MMStar
The official leaderboard hasn’t scored a model released after GPT-5 (August 2025). Labs report their own numbers for 30 newer models, such as Qwen 3.8 Max at 85.9%.
Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy.
- Made by
- USTC and Shanghai AI Laboratory
- Released
- March 2024
- Kind
- General visual questions
- Level
- School
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision
- Strongest model tested
-
Qwen 3.8 Max #30 on the capability index
- Last in a launch post
- October 2026
- Last model added
- October 2026
- Scores refreshed
- November 18th, 2026
In the authors’ words
Large vision-language models (LVLMs) have recently achieved rapid progress, sparking numerous studies to evaluate their multi-modal capabilities. However, we dig into current evaluation works and identify two primary issues: 1) Visual content is unnecessary for many samples. The answers can be directly inferred from the questions and options, or the world knowledge embedded in LLMs. This phenomenon is prevalent across current benchmarks. For instance, GeminiPro achieves 42.9% on the MMMU benchmark without any visual input, and outperforms the random choice baseline across six benchmarks over 24% on average. 2) Unintentional data leakage exists in LLM and LVLM training. LLM and LVLM could still answer some visual-necessary questions without visual content, indicating the memorizing of these samples within large-scale training data. For example, Sphinx-X-MoE gets 43.6% on MMMU without accessing images, surpassing its LLM backbone with 17.9%. Both problems lead to misjudgments of actual multi-modal gains and potentially misguide the study of LVLM. To this end, we present MMStar, an elite vision-indispensable multi-modal benchmark comprising 1,500 samples meticulously selected by humans. MMStar benchmarks 6 core capabilities and 18 detailed axes, aiming to evaluate LVLMs' multi-modal capacities with carefully balanced and purified samples. These samples are first roughly selected from current benchmarks with an automated pipeline, human review is then involved to ensure each curated sample exhibits visual dependency, minimal data leakage, and requires advanced multi-modal capabilities. Moreover, two metrics are developed to measure data leakage and actual performance gain in multi-modal training. We evaluate 16 leading LVLMs on MMStar to assess their multi-modal capabilities, and on 7 benchmarks with the proposed metrics to investigate their data leakage and actual multi-modal gain.
Qwen 3.8 Max leads with 85.9%
Best score per model as labs report them in their own cards, drawn striped. Labs pick their own settings, so these compare less cleanly than independent runs.
GPT-5 leads with 75.7% across all independent runs
Best score per model across the official leaderboard, Epoch AI’s own runs and any board Epoch AI copied. Dotted bars are reruns by Epoch AI or another board, and each row names its source.
Qwen 3.8 Max leads with 85.9%, claims included
Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model. Striped bars are claims, and dotted bars are reruns by Epoch AI or another board.
- 85.9
Qwen 3.8 Max
- 83.8
Qwen3.5 397B-A17B
- 83.3
Qwen 3.6 Plus
- 83.0
Seed2.0 Pro
- 82.9
Qwen3.5-122B-A10B
- 81.9
Qwen3.5-35B-A3B
- 81.4
Qwen3.6 27B
- 81.0
Qwen3.5-27B
- 80.7
MiniCPM-V-4.7-35B-A3B
- 79.9
Seed1.8
- 79.7
Qwen3.5-9B
- 79.4
Qwen3.5-Omni-Plus
- 78.7
Qwen3-VL-235B-A22B
- 78.3
Qwen3.5-4B
- 77.9
InternVL3.5-241B-A28B
- 77.8
Seed1.5-VL
- 77.5
STEP3-VL-10B
- 75.9 GLM-4.6V
- 75.9
Keye-VL-2.0-30B-A3B
- 75.5
ERNIE 5.0
- 75.3 GLM-4.5V
- 74.9
Intern-S1
- 74.9
EXAONE 4.5 33B
- 72.9 GLM-4.1V-9B-Thinking
- 71.7
Nemotron Nano 12B v2 VL
- 71.7
Qwen3.5-2B
- 71.1
ERNIE-4.5-VL-28B-A3B-Thinking
- 70.9
LongCat-Flash-Omni
- 70.8
Qwen2.5-VL-72B
- 70.4 Kimi-VL-A3B-Thinking-2506
- 68.5
Qwen3-Omni-30B-A3B
- 64.5
Phi-4-Reasoning-Vision-15B
- 64.0
Qwen2.5-Omni-7B
- 63.3 LFM2.5-VL-3B
- 58.3
Qwen3.5-0.8B
- 51.8
North Micro Vision Instruct
- 49.9 LFM2-VL-1.6B
- 1
Qwen 3.8 Max 85.9%
- 2
Qwen3.5 397B-A17B 83.8%
- 3
Qwen 3.6 Plus 83.3%
- 4
Seed2.0 Pro 83%
- 5
Qwen3.5-122B-A10B 82.9%
- 6
Qwen3.5-35B-A3B 81.9%
- 7
Qwen3.6 27B 81.4%
- 8
Qwen3.5-27B 81%
- 9
MiniCPM-V-4.7-35B-A3B 80.7%
- 10
Seed1.8 79.9%
- 11
Qwen3.5-9B 79.7%
- 12
Qwen3.5-Omni-Plus 79.4%
- 13
Qwen3-VL-235B-A22B 78.7%
- 14
Qwen3.5-4B 78.3%
- 15
InternVL3.5-241B-A28B 77.9%
- 16
Seed1.5-VL 77.8%
- 17
STEP3-VL-10B 77.5%
- 18 GLM-4.6V 75.9%
- 19
Keye-VL-2.0-30B-A3B 75.9%
- 20
ERNIE 5.0 75.5%
- 21 GLM-4.5V 75.3%
- 22
Intern-S1 74.9%
- 23
EXAONE 4.5 33B 74.9%
- 24 GLM-4.1V-9B-Thinking 72.9%
- 25
Nemotron Nano 12B v2 VL 71.7%
- 26
Qwen3.5-2B 71.7%
- 27
ERNIE-4.5-VL-28B-A3B-Thinking 71.1%
- 28
LongCat-Flash-Omni 70.9%
- 29
Qwen2.5-VL-72B 70.8%
- 30 Kimi-VL-A3B-Thinking-2506 70.4%
- 31
Qwen3-Omni-30B-A3B 68.5%
- 32
Phi-4-Reasoning-Vision-15B 64.5%
- 33
Qwen2.5-Omni-7B 64%
- 34 LFM2.5-VL-3B 63.3%
- 35
Qwen3.5-0.8B 58.3%
- 36
North Micro Vision Instruct 51.8%
- 37 LFM2-VL-1.6B 49.9%
Source: Labs’ model cards
- 75.7 GPT-5
- 73.6
Gemini 2.5 Pro
- 73.4
InternVL3-78B
- 73.2 GPT-5 mini
- 72.6
InternVL3-38B
- 72.1
InternVL2.5-78B-MPO
- 70.5
Qwen2.5-VL-72B
- 70.3
Qwen2.5-VL-32B
- 70.1
InternVL2.5-38B-MPO
- 70.0 Kimi-VL-A3B-Thinking-2506
- 69.8 GPT-4.1
- 69.5
InternVL2_5-78B
- 69.5
SAIL-VL-1.6-8B
- 69.4
Gemini 2.0 Flash
- 69.3 GPT-4.5
- 69.2
Ovis2-34B
- 68.9
InternVL3-14B
- 68.7
InternVL3-8B
- 68.6 Qwen2-VL-72B-Instruct
- 68.5
InternVL2.5-38B
- 68.5
Gemini 2.0 Pro
- 68.3 GPT-5 nano
- 67.7
InternVL2.5-26B-MPO
- 67.4
InternVL3-9B
- 67.2
Ovis2-16B
- 67.1
InternVL2-Llama3-76B
- 67.1
Gemini 1.5 Pro
- 66.5
InternVL2.5-26B
- 65.8 LLaVA-OneVision 72B
- 65.2 Grok 2 Vision (1212)
- 65.2
InternVL2.5-8B-MPO
- 65.1 Claude 3.5 Sonnet (October 2024)
- 65.1 GPT-4o
- 65.1 Claude 3.7 Sonnet
- 64.7
InternVL2-40B
- 64.7 GPT-4o
- 64.6
Ovis2-8B
- 64.4
Gemini 1.5 Flash
- 64.1
Qwen2.5-VL-7B
- 63.9 GPT-4o
- 63.7
NVLM-D-72B
- 63.5
Ovis1.6-Gemma2-27B
- 63.3
Molmo-72B
- 63.3 MiniCPM-o-2_6
- 63.2
InternVL2.5-8B
- 62.9
Ovis1.6-Gemma2-9B
- 62.5
InternVL2-8B-MPO
- 62.2 Claude 3.5 Sonnet
- 62.0 Kimi-VL-A3B-Instruct
- 61.9
LLaVA-OneVision 7B
- 61.9
DeepSeek-VL2
- 61.9
Ovis2-4B
- 61.5
InternVL2-8B
- 61.1
InternVL3-2B
- 61.0
InternVL2-26B
- 61.0
InternVL2.5-4B-MPO
- 60.9 GPT-4.1 mini
- 60.8 Kimi-VL-A3B-Thinking
- 60.7 Qwen2-VL-7B-Instruct
- 60.7 Aria
- 60.2 VITA-1.5
- 59.9
InternLM-XComposer2.5-7B
- 59.6
Gemma 3 27B
- 59.1
Gemini 1.5 Pro
- 58.9
Phi-4-multimodal
- 58.7
InternVL2.5-4B
- 58.1
Ovis1.5-Gemma2-9B
- 57.5 MiniCPM-V-2_6
- 57.5
DeepSeek-VL2-Small
- 57.3
Ovis1.5-Llama3-8B
- 57.1 InternVL-Chat-V1-5
- 56.7
LLaVA-OneVision 7B (SI)
- 56.7
Ovis2-2B
- 56.5
SAIL-VL-2B
- 56.3
Qwen2.5-VL-3B
- 56.1
Molmo-7B-D
- 56.1
Gemma 3 12B
- 56.0 GPT-4V
- 55.5
Eagle-X5-34B-Chat
- 55.3
InternLM-XComposer2-4KHD-7B
- 55.3
Llama 3.2 90B
- 55.2
VILA1.5-40B
- 55.0
Idefics3-8B-Llama3
- 54.9 Aquila-VL-2B
- 54.9
InternVL2.5-2B-MPO
- 54.8 GLM-4V-9B
- 54.8 GPT-4o mini
- 54.6 Granite Vision 3.2 2B
- 54.5
Pixtral 12B
- 54.3
InternVL2.5-2B
- 54.2
Cambrian-1-34B
- 53.9
InternVL2-4B
- 53.1
Mini-InternVL-Chat-4B-V1-5
- 52.3
InternVL3-1B
- 52.1
Ovis2-1B
- 52.0
Ovis1.6-Llama3.2-3B
- 51.9 Granite Vision 3.3 2B
- 51.8
MiniCPM-Llama3-V 2.5
- 51.6
LLaVA-v1.6-34B
- 51.3
InternVL2.5-1B
- 50.7
Cambrian-1-8B
- 50.5 CogVLM2-19B-Chat
- 50.2 Reka Flash
- 50.1
Molmo-7B-O
- 49.8
InternVL2-2B
- 49.8
Llama 3.2 11B
- 49.8
DeepSeek-VL2-Tiny
- 49.5 Qwen-VL-Max
- 49.5
Idefics2-8B
- 49.5
InternVL2.5-1B-MPO
- 48.3
PaliGemma-3B-mix-448
- 47.9
Gemma 3 4B
- 47.7
Phi-3-vision-128k-instruct
- 47.5 Phi-3.5-vision-instruct
- 47.5
Qwen2-VL-2B-Instruct
- 47.5 GPT-4.1 nano
- 47.1
Cambrian-1-13B
- 46.7
Mini-InternVL-Chat-2B-V1-5
- 46.6 VITA
- 46.6 Emu3-Chat
- 46.5
Janus-Pro-7B
- 46.4
InternLM-XComposer2-VL-1.8B
- 46.0
SmolVLM2-2.2B-Instruct
- 45.7 Claude 3 Opus
- 45.6
InternVL2-1B
- 45.4 Bunny-Llama-3-8B-V
- 45.4
Falcon2-11B-VLM
- 45.3
LLaVA-NeXT-Interleave-7B-DPO
- 44.5
LLaVA-NeXT-Interleave-7B
- 44.2 Claude 3 Sonnet
- 44.2
VILA1.5-13B
- 43.9 llama3-llava-next-8b
- 43.7
Eagle-X5-13B
- 43.1
MolmoE-1B
- 41.7
Eagle-X5-7B
- 41.7
SmolVLM-Instruct
- 40.7 Emu2-Chat
- 40.7 Monkey-Chat
- 40.6
VILA1.5-3B
- 40.5
Yi-VL-34B
- 40.5
DeepSeek-VL-7B-Chat
- 40.4 llava-v1.6-vicuna-13b
- 39.9 CogVLM-17B-Chat
- 39.9
DeepSeek-VL-1.3B-Chat
- 39.7
Qwen-VL-Plus
- 39.7
Llama-3-VILA1.5-8B
- 39.6
OmniLMM-12B
- 39.1
MiniCPM-V 2.0
- 38.6
Gemini 1.0 Pro
- 38.6
MiniCPM-V
- 38.4 llava-v1.6-mistral-7b
- 38.3
ShareGPT4V-13B
- 38.3
SmolVLM-500M-Instruct
- 38.2
SmolVLM2-500M-Video-Instruct
- 38.1 Claude 3 Haiku
- 37.7
Yi-VL-6B
- 37.7
LLaVA-OneVision 0.5B
- 37.6 llava-v1.6-vicuna-7b
- 37.6
Janus-1.3B
- 37.5
LLaVA-OneVision 0.5B (SI)
- 37.0 Monkey
- 35.7
ShareGPT4V-7B
- 34.8
mPLUG-Owl2
- 34.5 Qwen-VL-Chat
- 34.5
SmolVLM-256M-Instruct
- 34.3
LLaVA-v1.5-13B
- 33.1 llava-v1.5-7b
- 32.7 instructblip-vicuna-7b
- 31.8
Chameleon-30B
- 31.1
Chameleon-7B
- 30.9
SmolVLM2-256M-Video-Instruct
- 26.1
IDEFICS-80B-Instruct
- 24.9
Kosmos-2
- 21.6
IDEFICS-9B-Instruct
- 1 GPT-5 ✓ 75.7%
- 2
Gemini 2.5 Pro Mar 2025 ✓ 73.6%
- 3
InternVL3-78B ✓ 73.4%
- 4 GPT-5 mini ✓ 73.2%
- 5
InternVL3-38B ✓ 72.6%
- 6
InternVL2.5-78B-MPO ✓ 72.1%
- 7
Qwen2.5-VL-72B ✓ 70.5%
- 8
Qwen2.5-VL-32B ✓ 70.3%
- 9
InternVL2.5-38B-MPO ✓ 70.1%
- 10 Kimi-VL-A3B-Thinking-2506 ✓ 70%
- 11 GPT-4.1 ✓ 69.8%
- 12
InternVL2_5-78B ✓ 69.5%
- 13
SAIL-VL-1.6-8B ✓ 69.5%
- 14
Gemini 2.0 Flash Dec 2024 ✓ 69.4%
- 15 GPT-4.5 ✓ 69.3%
- 16
Ovis2-34B ✓ 69.2%
- 17
InternVL3-14B ✓ 68.9%
- 18
InternVL3-8B ✓ 68.7%
- 19 Qwen2-VL-72B-Instruct ✓ 68.6%
- 20
InternVL2.5-38B ✓ 68.5%
- 21
Gemini 2.0 Pro ✓ 68.5%
- 22 GPT-5 nano ✓ 68.3%
- 23
InternVL2.5-26B-MPO ✓ 67.7%
- 24
InternVL3-9B ✓ 67.4%
- 25
Ovis2-16B ✓ 67.2%
- 26
InternVL2-Llama3-76B ✓ 67.1%
- 27
Gemini 1.5 Pro Sep 2024 ✓ 67.1%
- 28
InternVL2.5-26B ✓ 66.5%
- 29 LLaVA-OneVision 72B ✓ 65.8%
- 30 Grok 2 Vision (1212) ✓ 65.2%
- 31
InternVL2.5-8B-MPO ✓ 65.2%
- 32 Claude 3.5 Sonnet (October 2024) ✓ 65.1%
- 33 GPT-4o Nov 2024, detail-high ✓ 65.1%
- 34 Claude 3.7 Sonnet ✓ 65.1%
- 35
InternVL2-40B ✓ 64.7%
- 36 GPT-4o Aug 2024, detail-high ✓ 64.7%
- 37
Ovis2-8B ✓ 64.6%
- 38
Gemini 1.5 Flash Sep 2024 ✓ 64.4%
- 39
Qwen2.5-VL-7B ✓ 64.1%
- 40 GPT-4o May 2024, detail-high ✓ 63.9%
- 41
NVLM-D-72B ✓ 63.7%
- 42
Ovis1.6-Gemma2-27B ✓ 63.5%
- 43
Molmo-72B ✓ 63.3%
- 44 MiniCPM-o-2_6 ✓ 63.3%
- 45
InternVL2.5-8B ✓ 63.2%
- 46
Ovis1.6-Gemma2-9B ✓ 62.9%
- 47
InternVL2-8B-MPO ✓ 62.5%
- 48 Claude 3.5 Sonnet ✓ 62.2%
- 49 Kimi-VL-A3B-Instruct ✓ 62%
- 50
LLaVA-OneVision 7B ✓ 61.9%
- 51
DeepSeek-VL2 ✓ 61.9%
- 52
Ovis2-4B ✓ 61.9%
- 53
InternVL2-8B ✓ 61.5%
- 54
InternVL3-2B ✓ 61.1%
- 55
InternVL2-26B ✓ 61%
- 56
InternVL2.5-4B-MPO ✓ 61%
- 57 GPT-4.1 mini ✓ 60.9%
- 58 Kimi-VL-A3B-Thinking ✓ 60.8%
- 59 Qwen2-VL-7B-Instruct ✓ 60.7%
- 60 Aria ✓ 60.7%
- 61 VITA-1.5 ✓ 60.2%
- 62
InternLM-XComposer2.5-7B ✓ 59.9%
- 63
Gemma 3 27B ✓ 59.6%
- 64
Gemini 1.5 Pro May 2024 ✓ 59.1%
- 65
Phi-4-multimodal ✓ 58.9%
- 66
InternVL2.5-4B ✓ 58.7%
- 67
Ovis1.5-Gemma2-9B ✓ 58.1%
- 68 MiniCPM-V-2_6 ✓ 57.5%
- 69
DeepSeek-VL2-Small ✓ 57.5%
- 70
Ovis1.5-Llama3-8B ✓ 57.3%
- 71 InternVL-Chat-V1-5 ✓ 57.1%
- 72
LLaVA-OneVision 7B (SI) ✓ 56.7%
- 73
Ovis2-2B ✓ 56.7%
- 74
SAIL-VL-2B ✓ 56.5%
- 75
Qwen2.5-VL-3B ✓ 56.3%
- 76
Molmo-7B-D ✓ 56.1%
- 77
Gemma 3 12B ✓ 56.1%
- 78 GPT-4V detail-high ✓ 56%
- 79
Eagle-X5-34B-Chat ✓ 55.5%
- 80
InternLM-XComposer2-4KHD-7B ✓ 55.3%
- 81
Llama 3.2 90B ✓ 55.3%
- 82
VILA1.5-40B ✓ 55.2%
- 83
Idefics3-8B-Llama3 ✓ 55%
- 84 Aquila-VL-2B ✓ 54.9%
- 85
InternVL2.5-2B-MPO ✓ 54.9%
- 86 GLM-4V-9B ✓ 54.8%
- 87 GPT-4o mini detail-high ✓ 54.8%
- 88 Granite Vision 3.2 2B ✓ 54.6%
- 89
Pixtral 12B ✓ 54.5%
- 90
InternVL2.5-2B ✓ 54.3%
- 91
Cambrian-1-34B ✓ 54.2%
- 92
InternVL2-4B ✓ 53.9%
- 93
Mini-InternVL-Chat-4B-V1-5 ✓ 53.1%
- 94
InternVL3-1B ✓ 52.3%
- 95
Ovis2-1B ✓ 52.1%
- 96
Ovis1.6-Llama3.2-3B ✓ 52%
- 97 Granite Vision 3.3 2B ✓ 51.9%
- 98
MiniCPM-Llama3-V 2.5 ✓ 51.8%
- 99
LLaVA-v1.6-34B ✓ 51.6%
- 100
InternVL2.5-1B ✓ 51.3%
- 101
Cambrian-1-8B ✓ 50.7%
- 102 CogVLM2-19B-Chat ✓ 50.5%
- 103 Reka Flash ✓ 50.2%
- 104
Molmo-7B-O ✓ 50.1%
- 105
InternVL2-2B ✓ 49.8%
- 106
Llama 3.2 11B ✓ 49.8%
- 107
DeepSeek-VL2-Tiny ✓ 49.8%
- 108 Qwen-VL-Max ✓ 49.5%
- 109
Idefics2-8B ✓ 49.5%
- 110
InternVL2.5-1B-MPO ✓ 49.5%
- 111
PaliGemma-3B-mix-448 ✓ 48.3%
- 112
Gemma 3 4B ✓ 47.9%
- 113
Phi-3-vision-128k-instruct ✓ 47.7%
- 114 Phi-3.5-vision-instruct ✓ 47.5%
- 115
Qwen2-VL-2B-Instruct ✓ 47.5%
- 116 GPT-4.1 nano ✓ 47.5%
- 117
Cambrian-1-13B ✓ 47.1%
- 118
Mini-InternVL-Chat-2B-V1-5 ✓ 46.7%
- 119 VITA ✓ 46.6%
- 120 Emu3-Chat ✓ 46.6%
- 121
Janus-Pro-7B ✓ 46.5%
- 122
InternLM-XComposer2-VL-1.8B ✓ 46.4%
- 123
SmolVLM2-2.2B-Instruct ✓ 46%
- 124 Claude 3 Opus ✓ 45.7%
- 125
InternVL2-1B ✓ 45.6%
- 126 Bunny-Llama-3-8B-V ✓ 45.4%
- 127
Falcon2-11B-VLM ✓ 45.4%
- 128
LLaVA-NeXT-Interleave-7B-DPO ✓ 45.3%
- 129
LLaVA-NeXT-Interleave-7B ✓ 44.5%
- 130 Claude 3 Sonnet ✓ 44.2%
- 131
VILA1.5-13B ✓ 44.2%
- 132 llama3-llava-next-8b ✓ 43.9%
- 133
Eagle-X5-13B ✓ 43.7%
- 134
MolmoE-1B ✓ 43.1%
- 135
Eagle-X5-7B ✓ 41.7%
- 136
SmolVLM-Instruct ✓ 41.7%
- 137 Emu2-Chat ✓ 40.7%
- 138 Monkey-Chat ✓ 40.7%
- 139
VILA1.5-3B ✓ 40.6%
- 140
Yi-VL-34B ✓ 40.5%
- 141
DeepSeek-VL-7B-Chat ✓ 40.5%
- 142 llava-v1.6-vicuna-13b ✓ 40.4%
- 143 CogVLM-17B-Chat ✓ 39.9%
- 144
DeepSeek-VL-1.3B-Chat ✓ 39.9%
- 145
Qwen-VL-Plus ✓ 39.7%
- 146
Llama-3-VILA1.5-8B ✓ 39.7%
- 147
OmniLMM-12B ✓ 39.6%
- 148
MiniCPM-V 2.0 ✓ 39.1%
- 149
Gemini 1.0 Pro ✓ 38.6%
- 150
MiniCPM-V ✓ 38.6%
- 151 llava-v1.6-mistral-7b ✓ 38.4%
- 152
ShareGPT4V-13B ✓ 38.3%
- 153
SmolVLM-500M-Instruct ✓ 38.3%
- 154
SmolVLM2-500M-Video-Instruct ✓ 38.2%
- 155 Claude 3 Haiku ✓ 38.1%
- 156
Yi-VL-6B ✓ 37.7%
- 157
LLaVA-OneVision 0.5B ✓ 37.7%
- 158 llava-v1.6-vicuna-7b ✓ 37.6%
- 159
Janus-1.3B ✓ 37.6%
- 160
LLaVA-OneVision 0.5B (SI) ✓ 37.5%
- 161 Monkey ✓ 37%
- 162
ShareGPT4V-7B ✓ 35.7%
- 163
mPLUG-Owl2 ✓ 34.8%
- 164 Qwen-VL-Chat ✓ 34.5%
- 165
SmolVLM-256M-Instruct ✓ 34.5%
- 166
LLaVA-v1.5-13B ✓ 34.3%
- 167 llava-v1.5-7b ✓ 33.1%
- 168 instructblip-vicuna-7b ✓ 32.7%
- 169
Chameleon-30B ✓ 31.8%
- 170
Chameleon-7B ✓ 31.1%
- 171
SmolVLM2-256M-Video-Instruct ✓ 30.9%
- 172
IDEFICS-80B-Instruct ✓ 26.1%
- 173
Kosmos-2 ✓ 24.9%
- 174
IDEFICS-9B-Instruct ✓ 21.6%
Source: Official MMStar leaderboard
- 85.9
Qwen 3.8 Max
- 83.8
Qwen3.5 397B-A17B
- 83.3
Qwen 3.6 Plus
- 83.0
Seed2.0 Pro
- 82.9
Qwen3.5-122B-A10B
- 81.9
Qwen3.5-35B-A3B
- 81.4
Qwen3.6 27B
- 81.0
Qwen3.5-27B
- 80.7
MiniCPM-V-4.7-35B-A3B
- 79.9
Seed1.8
- 79.7
Qwen3.5-9B
- 79.4
Qwen3.5-Omni-Plus
- 78.7
Qwen3-VL-235B-A22B
- 78.3
Qwen3.5-4B
- 77.9
InternVL3.5-241B-A28B
- 77.8
Seed1.5-VL
- 77.5
STEP3-VL-10B
- 75.9 GLM-4.6V
- 75.9
Keye-VL-2.0-30B-A3B
- 75.7 GPT-5
- 75.5
ERNIE 5.0
- 75.3 GLM-4.5V
- 74.9
Intern-S1
- 74.9
EXAONE 4.5 33B
- 73.6
Gemini 2.5 Pro
- 73.4
InternVL3-78B
- 73.2 GPT-5 mini
- 72.9 GLM-4.1V-9B-Thinking
- 72.6
InternVL3-38B
- 72.1
InternVL2.5-78B-MPO
- 71.7
Nemotron Nano 12B v2 VL
- 71.7
Qwen3.5-2B
- 71.1
ERNIE-4.5-VL-28B-A3B-Thinking
- 70.9
LongCat-Flash-Omni
- 70.8
Qwen2.5-VL-72B
- 70.4 Kimi-VL-A3B-Thinking-2506
- 70.3
Qwen2.5-VL-32B
- 70.1
InternVL2.5-38B-MPO
- 69.8 GPT-4.1
- 69.5
InternVL2_5-78B
- 69.5
SAIL-VL-1.6-8B
- 69.4
Gemini 2.0 Flash
- 69.3 GPT-4.5
- 69.2
Ovis2-34B
- 68.9
InternVL3-14B
- 68.7
InternVL3-8B
- 68.6 Qwen2-VL-72B-Instruct
- 68.5
InternVL2.5-38B
- 68.5
Gemini 2.0 Pro
- 68.5
Qwen3-Omni-30B-A3B
- 68.3 GPT-5 nano
- 67.7
InternVL2.5-26B-MPO
- 67.4
InternVL3-9B
- 67.2
Ovis2-16B
- 67.1
InternVL2-Llama3-76B
- 67.1
Gemini 1.5 Pro
- 66.5
InternVL2.5-26B
- 65.8 LLaVA-OneVision 72B
- 65.2 Grok 2 Vision (1212)
- 65.2
InternVL2.5-8B-MPO
- 65.1 Claude 3.5 Sonnet (October 2024)
- 65.1 GPT-4o
- 65.1 Claude 3.7 Sonnet
- 64.7
InternVL2-40B
- 64.7 GPT-4o
- 64.6
Ovis2-8B
- 64.5
Phi-4-Reasoning-Vision-15B
- 64.4
Gemini 1.5 Flash
- 64.1
Qwen2.5-VL-7B
- 64.0
Qwen2.5-Omni-7B
- 63.9 GPT-4o
- 63.7
NVLM-D-72B
- 63.5
Ovis1.6-Gemma2-27B
- 63.3
Molmo-72B
- 63.3 MiniCPM-o-2_6
- 63.3 LFM2.5-VL-3B
- 63.2
InternVL2.5-8B
- 62.9
Ovis1.6-Gemma2-9B
- 62.5
InternVL2-8B-MPO
- 62.2 Claude 3.5 Sonnet
- 62.0 Kimi-VL-A3B-Instruct
- 61.9
LLaVA-OneVision 7B
- 61.9
DeepSeek-VL2
- 61.9
Ovis2-4B
- 61.5
InternVL2-8B
- 61.1
InternVL3-2B
- 61.0
InternVL2-26B
- 61.0
InternVL2.5-4B-MPO
- 60.9 GPT-4.1 mini
- 60.8 Kimi-VL-A3B-Thinking
- 60.7 Qwen2-VL-7B-Instruct
- 60.7 Aria
- 60.2 VITA-1.5
- 59.9
InternLM-XComposer2.5-7B
- 59.6
Gemma 3 27B
- 59.1
Gemini 1.5 Pro
- 58.9
Phi-4-multimodal
- 58.7
InternVL2.5-4B
- 58.3
Qwen3.5-0.8B
- 58.1
Ovis1.5-Gemma2-9B
- 57.5 MiniCPM-V-2_6
- 57.5
DeepSeek-VL2-Small
- 57.3
Ovis1.5-Llama3-8B
- 57.1 InternVL-Chat-V1-5
- 56.7
LLaVA-OneVision 7B (SI)
- 56.7
Ovis2-2B
- 56.5
SAIL-VL-2B
- 56.3
Qwen2.5-VL-3B
- 56.1
Molmo-7B-D
- 56.1
Gemma 3 12B
- 56.0 GPT-4V
- 55.5
Eagle-X5-34B-Chat
- 55.3
InternLM-XComposer2-4KHD-7B
- 55.3
Llama 3.2 90B
- 55.2
VILA1.5-40B
- 55.0
Idefics3-8B-Llama3
- 54.9 Aquila-VL-2B
- 54.9
InternVL2.5-2B-MPO
- 54.8 GLM-4V-9B
- 54.8 GPT-4o mini
- 54.6 Granite Vision 3.2 2B
- 54.5
Pixtral 12B
- 54.3
InternVL2.5-2B
- 54.2
Cambrian-1-34B
- 53.9
InternVL2-4B
- 53.1
Mini-InternVL-Chat-4B-V1-5
- 52.3
InternVL3-1B
- 52.1
Ovis2-1B
- 52.0
Ovis1.6-Llama3.2-3B
- 51.9 Granite Vision 3.3 2B
- 51.8
MiniCPM-Llama3-V 2.5
- 51.8
North Micro Vision Instruct
- 51.6
LLaVA-v1.6-34B
- 51.3
InternVL2.5-1B
- 50.7
Cambrian-1-8B
- 50.5 CogVLM2-19B-Chat
- 50.2 Reka Flash
- 50.1
Molmo-7B-O
- 49.9 LFM2-VL-1.6B
- 49.8
InternVL2-2B
- 49.8
Llama 3.2 11B
- 49.8
DeepSeek-VL2-Tiny
- 49.5 Qwen-VL-Max
- 49.5
Idefics2-8B
- 49.5
InternVL2.5-1B-MPO
- 48.3
PaliGemma-3B-mix-448
- 47.9
Gemma 3 4B
- 47.7
Phi-3-vision-128k-instruct
- 47.5 Phi-3.5-vision-instruct
- 47.5
Qwen2-VL-2B-Instruct
- 47.5 GPT-4.1 nano
- 47.1
Cambrian-1-13B
- 46.7
Mini-InternVL-Chat-2B-V1-5
- 46.6 VITA
- 46.6 Emu3-Chat
- 46.5
Janus-Pro-7B
- 46.4
InternLM-XComposer2-VL-1.8B
- 46.0
SmolVLM2-2.2B-Instruct
- 45.7 Claude 3 Opus
- 45.6
InternVL2-1B
- 45.4 Bunny-Llama-3-8B-V
- 45.4
Falcon2-11B-VLM
- 45.3
LLaVA-NeXT-Interleave-7B-DPO
- 44.5
LLaVA-NeXT-Interleave-7B
- 44.2 Claude 3 Sonnet
- 44.2
VILA1.5-13B
- 43.9 llama3-llava-next-8b
- 43.7
Eagle-X5-13B
- 43.1
MolmoE-1B
- 41.7
Eagle-X5-7B
- 41.7
SmolVLM-Instruct
- 40.7 Emu2-Chat
- 40.7 Monkey-Chat
- 40.6
VILA1.5-3B
- 40.5
Yi-VL-34B
- 40.5
DeepSeek-VL-7B-Chat
- 40.4 llava-v1.6-vicuna-13b
- 39.9 CogVLM-17B-Chat
- 39.9
DeepSeek-VL-1.3B-Chat
- 39.7
Qwen-VL-Plus
- 39.7
Llama-3-VILA1.5-8B
- 39.6
OmniLMM-12B
- 39.1
MiniCPM-V 2.0
- 38.6
Gemini 1.0 Pro
- 38.6
MiniCPM-V
- 38.4 llava-v1.6-mistral-7b
- 38.3
ShareGPT4V-13B
- 38.3
SmolVLM-500M-Instruct
- 38.2
SmolVLM2-500M-Video-Instruct
- 38.1 Claude 3 Haiku
- 37.7
Yi-VL-6B
- 37.7
LLaVA-OneVision 0.5B
- 37.6 llava-v1.6-vicuna-7b
- 37.6
Janus-1.3B
- 37.5
LLaVA-OneVision 0.5B (SI)
- 37.0 Monkey
- 35.7
ShareGPT4V-7B
- 34.8
mPLUG-Owl2
- 34.5 Qwen-VL-Chat
- 34.5
SmolVLM-256M-Instruct
- 34.3
LLaVA-v1.5-13B
- 33.1 llava-v1.5-7b
- 32.7 instructblip-vicuna-7b
- 31.8
Chameleon-30B
- 31.1
Chameleon-7B
- 30.9
SmolVLM2-256M-Video-Instruct
- 26.1
IDEFICS-80B-Instruct
- 24.9
Kosmos-2
- 21.6
IDEFICS-9B-Instruct
- 1
Qwen 3.8 Max 85.9%
- 2
Qwen3.5 397B-A17B 83.8%
- 3
Qwen 3.6 Plus 83.3%
- 4
Seed2.0 Pro 83%
- 5
Qwen3.5-122B-A10B 82.9%
- 6
Qwen3.5-35B-A3B 81.9%
- 7
Qwen3.6 27B 81.4%
- 8
Qwen3.5-27B 81%
- 9
MiniCPM-V-4.7-35B-A3B 80.7%
- 10
Seed1.8 79.9%
- 11
Qwen3.5-9B 79.7%
- 12
Qwen3.5-Omni-Plus 79.4%
- 13
Qwen3-VL-235B-A22B 78.7%
- 14
Qwen3.5-4B 78.3%
- 15
InternVL3.5-241B-A28B 77.9%
- 16
Seed1.5-VL 77.8%
- 17
STEP3-VL-10B 77.5%
- 18 GLM-4.6V 75.9%
- 19
Keye-VL-2.0-30B-A3B 75.9%
- 20 GPT-5 ✓ 75.7%
- 21
ERNIE 5.0 75.5%
- 22 GLM-4.5V 75.3%
- 23
Intern-S1 74.9%
- 24
EXAONE 4.5 33B 74.9%
- 25
Gemini 2.5 Pro Mar 2025 ✓ 73.6%
- 26
InternVL3-78B ✓ 73.4%
- 27 GPT-5 mini ✓ 73.2%
- 28 GLM-4.1V-9B-Thinking 72.9%
- 29
InternVL3-38B ✓ 72.6%
- 30
InternVL2.5-78B-MPO ✓ 72.1%
- 31
Nemotron Nano 12B v2 VL 71.7%
- 32
Qwen3.5-2B 71.7%
- 33
ERNIE-4.5-VL-28B-A3B-Thinking 71.1%
- 34
LongCat-Flash-Omni 70.9%
- 35
Qwen2.5-VL-72B 70.8%
- 36 Kimi-VL-A3B-Thinking-2506 70.4%
- 37
Qwen2.5-VL-32B ✓ 70.3%
- 38
InternVL2.5-38B-MPO ✓ 70.1%
- 39 GPT-4.1 ✓ 69.8%
- 40
InternVL2_5-78B ✓ 69.5%
- 41
SAIL-VL-1.6-8B ✓ 69.5%
- 42
Gemini 2.0 Flash Dec 2024 ✓ 69.4%
- 43 GPT-4.5 ✓ 69.3%
- 44
Ovis2-34B ✓ 69.2%
- 45
InternVL3-14B ✓ 68.9%
- 46
InternVL3-8B ✓ 68.7%
- 47 Qwen2-VL-72B-Instruct ✓ 68.6%
- 48
InternVL2.5-38B ✓ 68.5%
- 49
Gemini 2.0 Pro ✓ 68.5%
- 50
Qwen3-Omni-30B-A3B 68.5%
- 51 GPT-5 nano ✓ 68.3%
- 52
InternVL2.5-26B-MPO ✓ 67.7%
- 53
InternVL3-9B ✓ 67.4%
- 54
Ovis2-16B ✓ 67.2%
- 55
InternVL2-Llama3-76B ✓ 67.1%
- 56
Gemini 1.5 Pro Sep 2024 ✓ 67.1%
- 57
InternVL2.5-26B ✓ 66.5%
- 58 LLaVA-OneVision 72B ✓ 65.8%
- 59 Grok 2 Vision (1212) ✓ 65.2%
- 60
InternVL2.5-8B-MPO ✓ 65.2%
- 61 Claude 3.5 Sonnet (October 2024) ✓ 65.1%
- 62 GPT-4o Nov 2024, detail-high ✓ 65.1%
- 63 Claude 3.7 Sonnet ✓ 65.1%
- 64
InternVL2-40B ✓ 64.7%
- 65 GPT-4o Aug 2024, detail-high ✓ 64.7%
- 66
Ovis2-8B ✓ 64.6%
- 67
Phi-4-Reasoning-Vision-15B 64.5%
- 68
Gemini 1.5 Flash Sep 2024 ✓ 64.4%
- 69
Qwen2.5-VL-7B ✓ 64.1%
- 70
Qwen2.5-Omni-7B 64%
- 71 GPT-4o May 2024, detail-high ✓ 63.9%
- 72
NVLM-D-72B ✓ 63.7%
- 73
Ovis1.6-Gemma2-27B ✓ 63.5%
- 74
Molmo-72B ✓ 63.3%
- 75 MiniCPM-o-2_6 ✓ 63.3%
- 76 LFM2.5-VL-3B 63.3%
- 77
InternVL2.5-8B ✓ 63.2%
- 78
Ovis1.6-Gemma2-9B ✓ 62.9%
- 79
InternVL2-8B-MPO ✓ 62.5%
- 80 Claude 3.5 Sonnet ✓ 62.2%
- 81 Kimi-VL-A3B-Instruct ✓ 62%
- 82
LLaVA-OneVision 7B ✓ 61.9%
- 83
DeepSeek-VL2 ✓ 61.9%
- 84
Ovis2-4B ✓ 61.9%
- 85
InternVL2-8B ✓ 61.5%
- 86
InternVL3-2B ✓ 61.1%
- 87
InternVL2-26B ✓ 61%
- 88
InternVL2.5-4B-MPO ✓ 61%
- 89 GPT-4.1 mini ✓ 60.9%
- 90 Kimi-VL-A3B-Thinking ✓ 60.8%
- 91 Qwen2-VL-7B-Instruct ✓ 60.7%
- 92 Aria ✓ 60.7%
- 93 VITA-1.5 ✓ 60.2%
- 94
InternLM-XComposer2.5-7B ✓ 59.9%
- 95
Gemma 3 27B ✓ 59.6%
- 96
Gemini 1.5 Pro May 2024 ✓ 59.1%
- 97
Phi-4-multimodal ✓ 58.9%
- 98
InternVL2.5-4B ✓ 58.7%
- 99
Qwen3.5-0.8B 58.3%
- 100
Ovis1.5-Gemma2-9B ✓ 58.1%
- 101 MiniCPM-V-2_6 ✓ 57.5%
- 102
DeepSeek-VL2-Small ✓ 57.5%
- 103
Ovis1.5-Llama3-8B ✓ 57.3%
- 104 InternVL-Chat-V1-5 ✓ 57.1%
- 105
LLaVA-OneVision 7B (SI) ✓ 56.7%
- 106
Ovis2-2B ✓ 56.7%
- 107
SAIL-VL-2B ✓ 56.5%
- 108
Qwen2.5-VL-3B ✓ 56.3%
- 109
Molmo-7B-D ✓ 56.1%
- 110
Gemma 3 12B ✓ 56.1%
- 111 GPT-4V detail-high ✓ 56%
- 112
Eagle-X5-34B-Chat ✓ 55.5%
- 113
InternLM-XComposer2-4KHD-7B ✓ 55.3%
- 114
Llama 3.2 90B ✓ 55.3%
- 115
VILA1.5-40B ✓ 55.2%
- 116
Idefics3-8B-Llama3 ✓ 55%
- 117 Aquila-VL-2B ✓ 54.9%
- 118
InternVL2.5-2B-MPO ✓ 54.9%
- 119 GLM-4V-9B ✓ 54.8%
- 120 GPT-4o mini detail-high ✓ 54.8%
- 121 Granite Vision 3.2 2B ✓ 54.6%
- 122
Pixtral 12B ✓ 54.5%
- 123
InternVL2.5-2B ✓ 54.3%
- 124
Cambrian-1-34B ✓ 54.2%
- 125
InternVL2-4B ✓ 53.9%
- 126
Mini-InternVL-Chat-4B-V1-5 ✓ 53.1%
- 127
InternVL3-1B ✓ 52.3%
- 128
Ovis2-1B ✓ 52.1%
- 129
Ovis1.6-Llama3.2-3B ✓ 52%
- 130 Granite Vision 3.3 2B ✓ 51.9%
- 131
MiniCPM-Llama3-V 2.5 ✓ 51.8%
- 132
North Micro Vision Instruct 51.8%
- 133
LLaVA-v1.6-34B ✓ 51.6%
- 134
InternVL2.5-1B ✓ 51.3%
- 135
Cambrian-1-8B ✓ 50.7%
- 136 CogVLM2-19B-Chat ✓ 50.5%
- 137 Reka Flash ✓ 50.2%
- 138
Molmo-7B-O ✓ 50.1%
- 139 LFM2-VL-1.6B 49.9%
- 140
InternVL2-2B ✓ 49.8%
- 141
Llama 3.2 11B ✓ 49.8%
- 142
DeepSeek-VL2-Tiny ✓ 49.8%
- 143 Qwen-VL-Max ✓ 49.5%
- 144
Idefics2-8B ✓ 49.5%
- 145
InternVL2.5-1B-MPO ✓ 49.5%
- 146
PaliGemma-3B-mix-448 ✓ 48.3%
- 147
Gemma 3 4B ✓ 47.9%
- 148
Phi-3-vision-128k-instruct ✓ 47.7%
- 149 Phi-3.5-vision-instruct ✓ 47.5%
- 150
Qwen2-VL-2B-Instruct ✓ 47.5%
- 151 GPT-4.1 nano ✓ 47.5%
- 152
Cambrian-1-13B ✓ 47.1%
- 153
Mini-InternVL-Chat-2B-V1-5 ✓ 46.7%
- 154 VITA ✓ 46.6%
- 155 Emu3-Chat ✓ 46.6%
- 156
Janus-Pro-7B ✓ 46.5%
- 157
InternLM-XComposer2-VL-1.8B ✓ 46.4%
- 158
SmolVLM2-2.2B-Instruct ✓ 46%
- 159 Claude 3 Opus ✓ 45.7%
- 160
InternVL2-1B ✓ 45.6%
- 161 Bunny-Llama-3-8B-V ✓ 45.4%
- 162
Falcon2-11B-VLM ✓ 45.4%
- 163
LLaVA-NeXT-Interleave-7B-DPO ✓ 45.3%
- 164
LLaVA-NeXT-Interleave-7B ✓ 44.5%
- 165 Claude 3 Sonnet ✓ 44.2%
- 166
VILA1.5-13B ✓ 44.2%
- 167 llama3-llava-next-8b ✓ 43.9%
- 168
Eagle-X5-13B ✓ 43.7%
- 169
MolmoE-1B ✓ 43.1%
- 170
Eagle-X5-7B ✓ 41.7%
- 171
SmolVLM-Instruct ✓ 41.7%
- 172 Emu2-Chat ✓ 40.7%
- 173 Monkey-Chat ✓ 40.7%
- 174
VILA1.5-3B ✓ 40.6%
- 175
Yi-VL-34B ✓ 40.5%
- 176
DeepSeek-VL-7B-Chat ✓ 40.5%
- 177 llava-v1.6-vicuna-13b ✓ 40.4%
- 178 CogVLM-17B-Chat ✓ 39.9%
- 179
DeepSeek-VL-1.3B-Chat ✓ 39.9%
- 180
Qwen-VL-Plus ✓ 39.7%
- 181
Llama-3-VILA1.5-8B ✓ 39.7%
- 182
OmniLMM-12B ✓ 39.6%
- 183
MiniCPM-V 2.0 ✓ 39.1%
- 184
Gemini 1.0 Pro ✓ 38.6%
- 185
MiniCPM-V ✓ 38.6%
- 186 llava-v1.6-mistral-7b ✓ 38.4%
- 187
ShareGPT4V-13B ✓ 38.3%
- 188
SmolVLM-500M-Instruct ✓ 38.3%
- 189
SmolVLM2-500M-Video-Instruct ✓ 38.2%
- 190 Claude 3 Haiku ✓ 38.1%
- 191
Yi-VL-6B ✓ 37.7%
- 192
LLaVA-OneVision 0.5B ✓ 37.7%
- 193 llava-v1.6-vicuna-7b ✓ 37.6%
- 194
Janus-1.3B ✓ 37.6%
- 195
LLaVA-OneVision 0.5B (SI) ✓ 37.5%
- 196 Monkey ✓ 37%
- 197
ShareGPT4V-7B ✓ 35.7%
- 198
mPLUG-Owl2 ✓ 34.8%
- 199 Qwen-VL-Chat ✓ 34.5%
- 200
SmolVLM-256M-Instruct ✓ 34.5%
- 201
LLaVA-v1.5-13B ✓ 34.3%
- 202 llava-v1.5-7b ✓ 33.1%
- 203 instructblip-vicuna-7b ✓ 32.7%
- 204
Chameleon-30B ✓ 31.8%
- 205
Chameleon-7B ✓ 31.1%
- 206
SmolVLM2-256M-Video-Instruct ✓ 30.9%
- 207
IDEFICS-80B-Instruct ✓ 26.1%
- 208
Kosmos-2 ✓ 24.9%
- 209
IDEFICS-9B-Instruct ✓ 21.6%
Sources: Labs’ model cards and official MMStar leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 85.9% | Aug 2026 | Lab model card | |
| 2 | | 83.8% | Feb 2026 | Lab model card | |
| 3 | | 83.3% | Apr 2026 | Lab model card | |
| 4 | | 83% | Feb 2026 | Lab model card | |
| 5 | | 82.9% | Feb 2026 | Lab model card | |
| 6 | | 81.9% | Feb 2026 | Lab model card | |
| 7 | | 81.4% | Apr 2026 | Lab model card | |
| 8 | | 81% | Feb 2026 | Lab model card | |
| 9 | | 80.7% | Oct 2026 | Lab model card | |
| 10 | | 79.9% | Dec 2025 | Lab model card | |
| 11 | | 79.7% | Mar 2026 | Lab model card | |
| 12 | | 79.4% | Mar 2026 | Lab model card | |
| 13 | | 78.7% | Sep 2025 | Lab model card | |
| 14 | | 78.3% | Mar 2026 | Lab model card | |
| 15 | | 77.9% | Aug 2025 | Lab model card | |
| 16 | | 77.8% | May 2025 | Lab model card | |
| 17 | | 77.5% | Jan 2026 | Lab model card | |
| 18 | GLM-4.6V | 75.9% | Dec 2025 | Lab model card | |
| 19 | | 75.9% | May 2026 | Lab model card | |
| 20 | | 75.5% | Feb 2026 | Lab model card | |
| 21 | GLM-4.5V | 75.3% | Aug 2025 | Lab model card | |
| 22 | | 74.9% | Jul 2025 | Lab model card | |
| 23 | | 74.9% | Apr 2026 | Lab model card | |
| 24 | GLM-4.1V-9B-Thinking | 72.9% | Jul 2025 | Lab model card | |
| 25 | | 71.7% | Nov 2025 | Lab model card | |
| 26 | | 71.7% | Mar 2026 | Lab model card | |
| 27 | | 71.1% | Nov 2025 | Lab model card | |
| 28 | | 70.9% | Oct 2025 | Lab model card | |
| 29 | | 70.8% | Jan 2025 | Lab model card | |
| 30 | Kimi-VL-A3B-Thinking-2506 | 70.4% | Jun 2025 | Lab model card | |
| 31 | | 68.5% | Sep 2025 | Lab model card | |
| 32 | | 64.5% | Mar 2026 | Lab model card | |
| 33 | | 64% | Mar 2025 | Lab model card | |
| 34 | LFM2.5-VL-3B | 63.3% | Aug 2026 | Lab model card | |
| 35 | | 58.3% | Mar 2026 | Lab model card | |
| 36 | | 51.8% | Aug 2026 | Lab model card | |
| 37 | LFM2-VL-1.6B | 49.9% | Nov 2025 | Lab model card |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5 | 75.7% | Aug 2025 | Official leaderboard | |
| 2 | 73.6% | Mar 2025 | Official leaderboard | ||
| 3 | 73.4% | Apr 2025 | Official leaderboard | ||
| 4 | GPT-5 mini | 73.2% | Aug 2025 | Official leaderboard | |
| 5 | 72.6% | Apr 2025 | Official leaderboard | ||
| 6 | 72.1% | Dec 2024 | Official leaderboard | ||
| 7 | 70.5% | Jan 2025 | Official leaderboard | ||
| 8 | 70.3% | Mar 2025 | Official leaderboard | ||
| 9 | 70.1% | Dec 2024 | Official leaderboard | ||
| 10 | Kimi-VL-A3B-Thinking-2506 | 70% | Jun 2025 | Official leaderboard | |
| 11 | GPT-4.1 | 69.8% | Apr 2025 | Official leaderboard | |
| 12 | 69.5% | Dec 2024 | Official leaderboard | ||
| 13 | 69.5% | Apr 2025 | Official leaderboard | ||
| 14 | 69.4% | Dec 2024 | Official leaderboard | ||
| 15 | GPT-4.5 | 69.3% | Feb 2025 | Official leaderboard | |
| 16 | 69.2% | Feb 2025 | Official leaderboard | ||
| 17 | 68.9% | Apr 2025 | Official leaderboard | ||
| 18 | 68.7% | Apr 2025 | Official leaderboard | ||
| 19 | Qwen2-VL-72B-Instruct | 68.6% | Aug 2024 | Official leaderboard | |
| 20 | 68.5% | Dec 2024 | Official leaderboard | ||
| 21 | 68.5% | Feb 2025 | Official leaderboard | ||
| 22 | GPT-5 nano | 68.3% | Aug 2025 | Official leaderboard | |
| 23 | 67.7% | Dec 2024 | Official leaderboard | ||
| 24 | 67.4% | Apr 2025 | Official leaderboard | ||
| 25 | 67.2% | Feb 2025 | Official leaderboard | ||
| 26 | 67.1% | Jul 2024 | Official leaderboard | ||
| 27 | 67.1% | Sep 2024 | Official leaderboard | ||
| 28 | 66.5% | Dec 2024 | Official leaderboard | ||
| 29 | LLaVA-OneVision 72B | 65.8% | Aug 2024 | Official leaderboard | |
| 30 | Grok 2 Vision (1212) | 65.2% | Dec 2024 | Official leaderboard | |
| 31 | 65.2% | Dec 2024 | Official leaderboard | ||
| 32 | Claude 3.5 Sonnet (October 2024) | 65.1% | Oct 2024 | Official leaderboard | |
| 33 | GPT-4o Nov 2024 | 65.1% | detail-high | Nov 2024 | Official leaderboard |
| 34 | Claude 3.7 Sonnet | 65.1% | Feb 2025 | Official leaderboard | |
| 35 | 64.7% | Jul 2024 | Official leaderboard | ||
| 36 | GPT-4o Aug 2024 | 64.7% | detail-high | Aug 2024 | Official leaderboard |
| 37 | 64.6% | Feb 2025 | Official leaderboard | ||
| 38 | 64.4% | Aug 2024 | Official leaderboard | ||
| 39 | 64.1% | Jan 2025 | Official leaderboard | ||
| 40 | GPT-4o May 2024 | 63.9% | detail-high | May 2024 | Official leaderboard |
| 41 | 63.7% | Sep 2024 | Official leaderboard | ||
| 42 | 63.5% | Nov 2024 | Official leaderboard | ||
| 43 | 63.3% | Sep 2024 | Official leaderboard | ||
| 44 | MiniCPM-o-2_6 | 63.3% | Jan 2025 | Official leaderboard | |
| 45 | 63.2% | Dec 2024 | Official leaderboard | ||
| 46 | 62.9% | Sep 2024 | Official leaderboard | ||
| 47 | 62.5% | Nov 2024 | Official leaderboard | ||
| 48 | Claude 3.5 Sonnet | 62.2% | Jun 2024 | Official leaderboard | |
| 49 | Kimi-VL-A3B-Instruct | 62% | Apr 2025 | Official leaderboard | |
| 50 | 61.9% | Aug 2024 | Official leaderboard | ||
| 51 | 61.9% | Dec 2024 | Official leaderboard | ||
| 52 | 61.9% | Feb 2025 | Official leaderboard | ||
| 53 | 61.5% | Jul 2024 | Official leaderboard | ||
| 54 | 61.1% | Apr 2025 | Official leaderboard | ||
| 55 | 61% | Jul 2024 | Official leaderboard | ||
| 56 | 61% | Dec 2024 | Official leaderboard | ||
| 57 | GPT-4.1 mini | 60.9% | Apr 2025 | Official leaderboard | |
| 58 | Kimi-VL-A3B-Thinking | 60.8% | Apr 2025 | Official leaderboard | |
| 59 | Qwen2-VL-7B-Instruct | 60.7% | Aug 2024 | Official leaderboard | |
| 60 | Aria | 60.7% | Sep 2024 | Official leaderboard | |
| 61 | VITA-1.5 | 60.2% | Dec 2024 | Official leaderboard | |
| 62 | 59.9% | Jul 2024 | Official leaderboard | ||
| 63 | 59.6% | Mar 2025 | Official leaderboard | ||
| 64 | 59.1% | May 2024 | Official leaderboard | ||
| 65 | 58.9% | Feb 2025 | Official leaderboard | ||
| 66 | 58.7% | Dec 2024 | Official leaderboard | ||
| 67 | 58.1% | Jul 2024 | Official leaderboard | ||
| 68 | MiniCPM-V-2_6 | 57.5% | Aug 2024 | Official leaderboard | |
| 69 | 57.5% | Dec 2024 | Official leaderboard | ||
| 70 | 57.3% | Jul 2024 | Official leaderboard | ||
| 71 | InternVL-Chat-V1-5 | 57.1% | Apr 2024 | Official leaderboard | |
| 72 | 56.7% | Aug 2024 | Official leaderboard | ||
| 73 | 56.7% | Feb 2025 | Official leaderboard | ||
| 74 | 56.5% | Dec 2024 | Official leaderboard | ||
| 75 | 56.3% | Jan 2025 | Official leaderboard | ||
| 76 | 56.1% | Sep 2024 | Official leaderboard | ||
| 77 | 56.1% | Mar 2025 | Official leaderboard | ||
| 78 | GPT-4V | 56% | detail-high | Nov 2023 | Official leaderboard |
| 79 | 55.5% | Sep 2024 | Official leaderboard | ||
| 80 | 55.3% | Apr 2024 | Official leaderboard | ||
| 81 | 55.3% | Sep 2024 | Official leaderboard | ||
| 82 | 55.2% | Apr 2024 | Official leaderboard | ||
| 83 | 55% | Aug 2024 | Official leaderboard | ||
| 84 | Aquila-VL-2B | 54.9% | Oct 2024 | Official leaderboard | |
| 85 | 54.9% | Dec 2024 | Official leaderboard | ||
| 86 | GLM-4V-9B | 54.8% | Jun 2024 | Official leaderboard | |
| 87 | GPT-4o mini | 54.8% | detail-high | Jul 2024 | Official leaderboard |
| 88 | Granite Vision 3.2 2B | 54.6% | Feb 2025 | Official leaderboard | |
| 89 | 54.5% | Sep 2024 | Official leaderboard | ||
| 90 | 54.3% | Dec 2024 | Official leaderboard | ||
| 91 | 54.2% | Jun 2024 | Official leaderboard | ||
| 92 | 53.9% | Jul 2024 | Official leaderboard | ||
| 93 | 53.1% | May 2024 | Official leaderboard | ||
| 94 | 52.3% | Apr 2025 | Official leaderboard | ||
| 95 | 52.1% | Feb 2025 | Official leaderboard | ||
| 96 | 52% | Oct 2024 | Official leaderboard | ||
| 97 | Granite Vision 3.3 2B | 51.9% | Jun 2025 | Official leaderboard | |
| 98 | 51.8% | May 2024 | Official leaderboard | ||
| 99 | 51.6% | Jan 2024 | Official leaderboard | ||
| 100 | 51.3% | Dec 2024 | Official leaderboard | ||
| 101 | 50.7% | Jun 2024 | Official leaderboard | ||
| 102 | CogVLM2-19B-Chat | 50.5% | May 2024 | Official leaderboard | |
| 103 | Reka Flash | 50.2% | Feb 2024 | Official leaderboard | |
| 104 | 50.1% | Sep 2024 | Official leaderboard | ||
| 105 | 49.8% | Jul 2024 | Official leaderboard | ||
| 106 | 49.8% | Sep 2024 | Official leaderboard | ||
| 107 | 49.8% | Dec 2024 | Official leaderboard | ||
| 108 | Qwen-VL-Max | 49.5% | Jan 2024 | Official leaderboard | |
| 109 | 49.5% | Apr 2024 | Official leaderboard | ||
| 110 | 49.5% | Dec 2024 | Official leaderboard | ||
| 111 | 48.3% | May 2024 | Official leaderboard | ||
| 112 | 47.9% | Mar 2025 | Official leaderboard | ||
| 113 | 47.7% | May 2024 | Official leaderboard | ||
| 114 | Phi-3.5-vision-instruct | 47.5% | Aug 2024 | Official leaderboard | |
| 115 | 47.5% | Aug 2024 | Official leaderboard | ||
| 116 | GPT-4.1 nano | 47.5% | Apr 2025 | Official leaderboard | |
| 117 | 47.1% | Jun 2024 | Official leaderboard | ||
| 118 | 46.7% | May 2024 | Official leaderboard | ||
| 119 | VITA | 46.6% | Aug 2024 | Official leaderboard | |
| 120 | Emu3-Chat | 46.6% | Sep 2024 | Official leaderboard | |
| 121 | 46.5% | Jan 2025 | Official leaderboard | ||
| 122 | 46.4% | Apr 2024 | Official leaderboard | ||
| 123 | 46% | Feb 2025 | Official leaderboard | ||
| 124 | Claude 3 Opus | 45.7% | Feb 2024 | Official leaderboard | |
| 125 | 45.6% | Jul 2024 | Official leaderboard | ||
| 126 | Bunny-Llama-3-8B-V | 45.4% | Apr 2024 | Official leaderboard | |
| 127 | 45.4% | May 2024 | Official leaderboard | ||
| 128 | 45.3% | Jun 2024 | Official leaderboard | ||
| 129 | 44.5% | Jun 2024 | Official leaderboard | ||
| 130 | Claude 3 Sonnet | 44.2% | Feb 2024 | Official leaderboard | |
| 131 | 44.2% | Apr 2024 | Official leaderboard | ||
| 132 | llama3-llava-next-8b | 43.9% | Apr 2024 | Official leaderboard | |
| 133 | 43.7% | Aug 2024 | Official leaderboard | ||
| 134 | 43.1% | Sep 2024 | Official leaderboard | ||
| 135 | 41.7% | Aug 2024 | Official leaderboard | ||
| 136 | 41.7% | Nov 2024 | Official leaderboard | ||
| 137 | Emu2-Chat | 40.7% | Dec 2023 | Official leaderboard | |
| 138 | Monkey-Chat | 40.7% | Jan 2024 | Official leaderboard | |
| 139 | 40.6% | Apr 2024 | Official leaderboard | ||
| 140 | 40.5% | Dec 2023 | Official leaderboard | ||
| 141 | 40.5% | Mar 2024 | Official leaderboard | ||
| 142 | llava-v1.6-vicuna-13b | 40.4% | Jan 2024 | Official leaderboard | |
| 143 | CogVLM-17B-Chat | 39.9% | Nov 2023 | Official leaderboard | |
| 144 | 39.9% | Mar 2024 | Official leaderboard | ||
| 145 | 39.7% | Jan 2024 | Official leaderboard | ||
| 146 | 39.7% | Apr 2024 | Official leaderboard | ||
| 147 | 39.6% | Jan 2024 | Official leaderboard | ||
| 148 | 39.1% | Apr 2024 | Official leaderboard | ||
| 149 | 38.6% | Dec 2023 | Official leaderboard | ||
| 150 | 38.6% | Jan 2024 | Official leaderboard | ||
| 151 | llava-v1.6-mistral-7b | 38.4% | Jan 2024 | Official leaderboard | |
| 152 | 38.3% | Dec 2023 | Official leaderboard | ||
| 153 | 38.3% | Jan 2025 | Official leaderboard | ||
| 154 | 38.2% | Feb 2025 | Official leaderboard | ||
| 155 | Claude 3 Haiku | 38.1% | Mar 2024 | Official leaderboard | |
| 156 | 37.7% | Dec 2023 | Official leaderboard | ||
| 157 | 37.7% | Aug 2024 | Official leaderboard | ||
| 158 | llava-v1.6-vicuna-7b | 37.6% | Jan 2024 | Official leaderboard | |
| 159 | 37.6% | Oct 2024 | Official leaderboard | ||
| 160 | 37.5% | Aug 2024 | Official leaderboard | ||
| 161 | Monkey | 37% | Nov 2023 | Official leaderboard | |
| 162 | 35.7% | Nov 2023 | Official leaderboard | ||
| 163 | 34.8% | Nov 2023 | Official leaderboard | ||
| 164 | Qwen-VL-Chat | 34.5% | Aug 2023 | Official leaderboard | |
| 165 | 34.5% | Jan 2025 | Official leaderboard | ||
| 166 | 34.3% | Oct 2023 | Official leaderboard | ||
| 167 | llava-v1.5-7b | 33.1% | Oct 2023 | Official leaderboard | |
| 168 | instructblip-vicuna-7b | 32.7% | May 2023 | Official leaderboard | |
| 169 | 31.8% | Jun 2024 | Official leaderboard | ||
| 170 | 31.1% | Jun 2024 | Official leaderboard | ||
| 171 | 30.9% | Feb 2025 | Official leaderboard | ||
| 172 | 26.1% | Jul 2023 | Official leaderboard | ||
| 173 | 24.9% | Jun 2023 | Official leaderboard | ||
| 174 | 21.6% | Jul 2023 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | 85.9% | Aug 2026 | Lab model card | ||
| 2 | 83.8% | Feb 2026 | Lab model card | ||
| 3 | 83.3% | Apr 2026 | Lab model card | ||
| 4 | 83% | Feb 2026 | Lab model card | ||
| 5 | 82.9% | Feb 2026 | Lab model card | ||
| 6 | 81.9% | Feb 2026 | Lab model card | ||
| 7 | 81.4% | Apr 2026 | Lab model card | ||
| 8 | 81% | Feb 2026 | Lab model card | ||
| 9 | 80.7% | Oct 2026 | Lab model card | ||
| 10 | 79.9% | Dec 2025 | Lab model card | ||
| 11 | 79.7% | Mar 2026 | Lab model card | ||
| 12 | 79.4% | Mar 2026 | Lab model card | ||
| 13 | 78.7% | Sep 2025 | Lab model card | ||
| 14 | 78.3% | Mar 2026 | Lab model card | ||
| 15 | 77.9% | Aug 2025 | Lab model card | ||
| 16 | 77.8% | May 2025 | Lab model card | ||
| 17 | 77.5% | Jan 2026 | Lab model card | ||
| 18 | GLM-4.6V | 75.9% | Dec 2025 | Lab model card | |
| 19 | 75.9% | May 2026 | Lab model card | ||
| 20 | GPT-5 | 75.7% | Aug 2025 | Official leaderboard | |
| 21 | 75.5% | Feb 2026 | Lab model card | ||
| 22 | GLM-4.5V | 75.3% | Aug 2025 | Lab model card | |
| 23 | 74.9% | Jul 2025 | Lab model card | ||
| 24 | 74.9% | Apr 2026 | Lab model card | ||
| 25 | 73.6% | Mar 2025 | Official leaderboard | ||
| 26 | 73.4% | Apr 2025 | Official leaderboard | ||
| 27 | GPT-5 mini | 73.2% | Aug 2025 | Official leaderboard | |
| 28 | GLM-4.1V-9B-Thinking | 72.9% | Jul 2025 | Lab model card | |
| 29 | 72.6% | Apr 2025 | Official leaderboard | ||
| 30 | 72.1% | Dec 2024 | Official leaderboard | ||
| 31 | 71.7% | Nov 2025 | Lab model card | ||
| 32 | 71.7% | Mar 2026 | Lab model card | ||
| 33 | 71.1% | Nov 2025 | Lab model card | ||
| 34 | 70.9% | Oct 2025 | Lab model card | ||
| 35 | 70.8% | Jan 2025 | Lab model card | ||
| 36 | Kimi-VL-A3B-Thinking-2506 | 70.4% | Jun 2025 | Lab model card | |
| 37 | 70.3% | Mar 2025 | Official leaderboard | ||
| 38 | 70.1% | Dec 2024 | Official leaderboard | ||
| 39 | GPT-4.1 | 69.8% | Apr 2025 | Official leaderboard | |
| 40 | 69.5% | Dec 2024 | Official leaderboard | ||
| 41 | 69.5% | Apr 2025 | Official leaderboard | ||
| 42 | 69.4% | Dec 2024 | Official leaderboard | ||
| 43 | GPT-4.5 | 69.3% | Feb 2025 | Official leaderboard | |
| 44 | 69.2% | Feb 2025 | Official leaderboard | ||
| 45 | 68.9% | Apr 2025 | Official leaderboard | ||
| 46 | 68.7% | Apr 2025 | Official leaderboard | ||
| 47 | Qwen2-VL-72B-Instruct | 68.6% | Aug 2024 | Official leaderboard | |
| 48 | 68.5% | Dec 2024 | Official leaderboard | ||
| 49 | 68.5% | Feb 2025 | Official leaderboard | ||
| 50 | 68.5% | Sep 2025 | Lab model card | ||
| 51 | GPT-5 nano | 68.3% | Aug 2025 | Official leaderboard | |
| 52 | 67.7% | Dec 2024 | Official leaderboard | ||
| 53 | 67.4% | Apr 2025 | Official leaderboard | ||
| 54 | 67.2% | Feb 2025 | Official leaderboard | ||
| 55 | 67.1% | Jul 2024 | Official leaderboard | ||
| 56 | 67.1% | Sep 2024 | Official leaderboard | ||
| 57 | 66.5% | Dec 2024 | Official leaderboard | ||
| 58 | LLaVA-OneVision 72B | 65.8% | Aug 2024 | Official leaderboard | |
| 59 | Grok 2 Vision (1212) | 65.2% | Dec 2024 | Official leaderboard | |
| 60 | 65.2% | Dec 2024 | Official leaderboard | ||
| 61 | Claude 3.5 Sonnet (October 2024) | 65.1% | Oct 2024 | Official leaderboard | |
| 62 | GPT-4o Nov 2024 | 65.1% | detail-high | Nov 2024 | Official leaderboard |
| 63 | Claude 3.7 Sonnet | 65.1% | Feb 2025 | Official leaderboard | |
| 64 | 64.7% | Jul 2024 | Official leaderboard | ||
| 65 | GPT-4o Aug 2024 | 64.7% | detail-high | Aug 2024 | Official leaderboard |
| 66 | 64.6% | Feb 2025 | Official leaderboard | ||
| 67 | 64.5% | Mar 2026 | Lab model card | ||
| 68 | 64.4% | Aug 2024 | Official leaderboard | ||
| 69 | 64.1% | Jan 2025 | Official leaderboard | ||
| 70 | 64% | Mar 2025 | Lab model card | ||
| 71 | GPT-4o May 2024 | 63.9% | detail-high | May 2024 | Official leaderboard |
| 72 | 63.7% | Sep 2024 | Official leaderboard | ||
| 73 | 63.5% | Nov 2024 | Official leaderboard | ||
| 74 | 63.3% | Sep 2024 | Official leaderboard | ||
| 75 | MiniCPM-o-2_6 | 63.3% | Jan 2025 | Official leaderboard | |
| 76 | LFM2.5-VL-3B | 63.3% | Aug 2026 | Lab model card | |
| 77 | 63.2% | Dec 2024 | Official leaderboard | ||
| 78 | 62.9% | Sep 2024 | Official leaderboard | ||
| 79 | 62.5% | Nov 2024 | Official leaderboard | ||
| 80 | Claude 3.5 Sonnet | 62.2% | Jun 2024 | Official leaderboard | |
| 81 | Kimi-VL-A3B-Instruct | 62% | Apr 2025 | Official leaderboard | |
| 82 | 61.9% | Aug 2024 | Official leaderboard | ||
| 83 | 61.9% | Dec 2024 | Official leaderboard | ||
| 84 | 61.9% | Feb 2025 | Official leaderboard | ||
| 85 | 61.5% | Jul 2024 | Official leaderboard | ||
| 86 | 61.1% | Apr 2025 | Official leaderboard | ||
| 87 | 61% | Jul 2024 | Official leaderboard | ||
| 88 | 61% | Dec 2024 | Official leaderboard | ||
| 89 | GPT-4.1 mini | 60.9% | Apr 2025 | Official leaderboard | |
| 90 | Kimi-VL-A3B-Thinking | 60.8% | Apr 2025 | Official leaderboard | |
| 91 | Qwen2-VL-7B-Instruct | 60.7% | Aug 2024 | Official leaderboard | |
| 92 | Aria | 60.7% | Sep 2024 | Official leaderboard | |
| 93 | VITA-1.5 | 60.2% | Dec 2024 | Official leaderboard | |
| 94 | 59.9% | Jul 2024 | Official leaderboard | ||
| 95 | 59.6% | Mar 2025 | Official leaderboard | ||
| 96 | 59.1% | May 2024 | Official leaderboard | ||
| 97 | 58.9% | Feb 2025 | Official leaderboard | ||
| 98 | 58.7% | Dec 2024 | Official leaderboard | ||
| 99 | 58.3% | Mar 2026 | Lab model card | ||
| 100 | 58.1% | Jul 2024 | Official leaderboard | ||
| 101 | MiniCPM-V-2_6 | 57.5% | Aug 2024 | Official leaderboard | |
| 102 | 57.5% | Dec 2024 | Official leaderboard | ||
| 103 | 57.3% | Jul 2024 | Official leaderboard | ||
| 104 | InternVL-Chat-V1-5 | 57.1% | Apr 2024 | Official leaderboard | |
| 105 | 56.7% | Aug 2024 | Official leaderboard | ||
| 106 | 56.7% | Feb 2025 | Official leaderboard | ||
| 107 | 56.5% | Dec 2024 | Official leaderboard | ||
| 108 | 56.3% | Jan 2025 | Official leaderboard | ||
| 109 | 56.1% | Sep 2024 | Official leaderboard | ||
| 110 | 56.1% | Mar 2025 | Official leaderboard | ||
| 111 | GPT-4V | 56% | detail-high | Nov 2023 | Official leaderboard |
| 112 | 55.5% | Sep 2024 | Official leaderboard | ||
| 113 | 55.3% | Apr 2024 | Official leaderboard | ||
| 114 | 55.3% | Sep 2024 | Official leaderboard | ||
| 115 | 55.2% | Apr 2024 | Official leaderboard | ||
| 116 | 55% | Aug 2024 | Official leaderboard | ||
| 117 | Aquila-VL-2B | 54.9% | Oct 2024 | Official leaderboard | |
| 118 | 54.9% | Dec 2024 | Official leaderboard | ||
| 119 | GLM-4V-9B | 54.8% | Jun 2024 | Official leaderboard | |
| 120 | GPT-4o mini | 54.8% | detail-high | Jul 2024 | Official leaderboard |
| 121 | Granite Vision 3.2 2B | 54.6% | Feb 2025 | Official leaderboard | |
| 122 | 54.5% | Sep 2024 | Official leaderboard | ||
| 123 | 54.3% | Dec 2024 | Official leaderboard | ||
| 124 | 54.2% | Jun 2024 | Official leaderboard | ||
| 125 | 53.9% | Jul 2024 | Official leaderboard | ||
| 126 | 53.1% | May 2024 | Official leaderboard | ||
| 127 | 52.3% | Apr 2025 | Official leaderboard | ||
| 128 | 52.1% | Feb 2025 | Official leaderboard | ||
| 129 | 52% | Oct 2024 | Official leaderboard | ||
| 130 | Granite Vision 3.3 2B | 51.9% | Jun 2025 | Official leaderboard | |
| 131 | 51.8% | May 2024 | Official leaderboard | ||
| 132 | 51.8% | Aug 2026 | Lab model card | ||
| 133 | 51.6% | Jan 2024 | Official leaderboard | ||
| 134 | 51.3% | Dec 2024 | Official leaderboard | ||
| 135 | 50.7% | Jun 2024 | Official leaderboard | ||
| 136 | CogVLM2-19B-Chat | 50.5% | May 2024 | Official leaderboard | |
| 137 | Reka Flash | 50.2% | Feb 2024 | Official leaderboard | |
| 138 | 50.1% | Sep 2024 | Official leaderboard | ||
| 139 | LFM2-VL-1.6B | 49.9% | Nov 2025 | Lab model card | |
| 140 | 49.8% | Jul 2024 | Official leaderboard | ||
| 141 | 49.8% | Sep 2024 | Official leaderboard | ||
| 142 | 49.8% | Dec 2024 | Official leaderboard | ||
| 143 | Qwen-VL-Max | 49.5% | Jan 2024 | Official leaderboard | |
| 144 | 49.5% | Apr 2024 | Official leaderboard | ||
| 145 | 49.5% | Dec 2024 | Official leaderboard | ||
| 146 | 48.3% | May 2024 | Official leaderboard | ||
| 147 | 47.9% | Mar 2025 | Official leaderboard | ||
| 148 | 47.7% | May 2024 | Official leaderboard | ||
| 149 | Phi-3.5-vision-instruct | 47.5% | Aug 2024 | Official leaderboard | |
| 150 | 47.5% | Aug 2024 | Official leaderboard | ||
| 151 | GPT-4.1 nano | 47.5% | Apr 2025 | Official leaderboard | |
| 152 | 47.1% | Jun 2024 | Official leaderboard | ||
| 153 | 46.7% | May 2024 | Official leaderboard | ||
| 154 | VITA | 46.6% | Aug 2024 | Official leaderboard | |
| 155 | Emu3-Chat | 46.6% | Sep 2024 | Official leaderboard | |
| 156 | 46.5% | Jan 2025 | Official leaderboard | ||
| 157 | 46.4% | Apr 2024 | Official leaderboard | ||
| 158 | 46% | Feb 2025 | Official leaderboard | ||
| 159 | Claude 3 Opus | 45.7% | Feb 2024 | Official leaderboard | |
| 160 | 45.6% | Jul 2024 | Official leaderboard | ||
| 161 | Bunny-Llama-3-8B-V | 45.4% | Apr 2024 | Official leaderboard | |
| 162 | 45.4% | May 2024 | Official leaderboard | ||
| 163 | 45.3% | Jun 2024 | Official leaderboard | ||
| 164 | 44.5% | Jun 2024 | Official leaderboard | ||
| 165 | Claude 3 Sonnet | 44.2% | Feb 2024 | Official leaderboard | |
| 166 | 44.2% | Apr 2024 | Official leaderboard | ||
| 167 | llama3-llava-next-8b | 43.9% | Apr 2024 | Official leaderboard | |
| 168 | 43.7% | Aug 2024 | Official leaderboard | ||
| 169 | 43.1% | Sep 2024 | Official leaderboard | ||
| 170 | 41.7% | Aug 2024 | Official leaderboard | ||
| 171 | 41.7% | Nov 2024 | Official leaderboard | ||
| 172 | Emu2-Chat | 40.7% | Dec 2023 | Official leaderboard | |
| 173 | Monkey-Chat | 40.7% | Jan 2024 | Official leaderboard | |
| 174 | 40.6% | Apr 2024 | Official leaderboard | ||
| 175 | 40.5% | Dec 2023 | Official leaderboard | ||
| 176 | 40.5% | Mar 2024 | Official leaderboard | ||
| 177 | llava-v1.6-vicuna-13b | 40.4% | Jan 2024 | Official leaderboard | |
| 178 | CogVLM-17B-Chat | 39.9% | Nov 2023 | Official leaderboard | |
| 179 | 39.9% | Mar 2024 | Official leaderboard | ||
| 180 | 39.7% | Jan 2024 | Official leaderboard | ||
| 181 | 39.7% | Apr 2024 | Official leaderboard | ||
| 182 | 39.6% | Jan 2024 | Official leaderboard | ||
| 183 | 39.1% | Apr 2024 | Official leaderboard | ||
| 184 | 38.6% | Dec 2023 | Official leaderboard | ||
| 185 | 38.6% | Jan 2024 | Official leaderboard | ||
| 186 | llava-v1.6-mistral-7b | 38.4% | Jan 2024 | Official leaderboard | |
| 187 | 38.3% | Dec 2023 | Official leaderboard | ||
| 188 | 38.3% | Jan 2025 | Official leaderboard | ||
| 189 | 38.2% | Feb 2025 | Official leaderboard | ||
| 190 | Claude 3 Haiku | 38.1% | Mar 2024 | Official leaderboard | |
| 191 | 37.7% | Dec 2023 | Official leaderboard | ||
| 192 | 37.7% | Aug 2024 | Official leaderboard | ||
| 193 | llava-v1.6-vicuna-7b | 37.6% | Jan 2024 | Official leaderboard | |
| 194 | 37.6% | Oct 2024 | Official leaderboard | ||
| 195 | 37.5% | Aug 2024 | Official leaderboard | ||
| 196 | Monkey | 37% | Nov 2023 | Official leaderboard | |
| 197 | 35.7% | Nov 2023 | Official leaderboard | ||
| 198 | 34.8% | Nov 2023 | Official leaderboard | ||
| 199 | Qwen-VL-Chat | 34.5% | Aug 2023 | Official leaderboard | |
| 200 | 34.5% | Jan 2025 | Official leaderboard | ||
| 201 | 34.3% | Oct 2023 | Official leaderboard | ||
| 202 | llava-v1.5-7b | 33.1% | Oct 2023 | Official leaderboard | |
| 203 | instructblip-vicuna-7b | 32.7% | May 2023 | Official leaderboard | |
| 204 | 31.8% | Jun 2024 | Official leaderboard | ||
| 205 | 31.1% | Jun 2024 | Official leaderboard | ||
| 206 | 30.9% | Feb 2025 | Official leaderboard | ||
| 207 | 26.1% | Jul 2023 | Official leaderboard | ||
| 208 | 24.9% | Jun 2023 | Official leaderboard | ||
| 209 | 21.6% | Jul 2023 | Official leaderboard |
The benchmark's own leaderboard has 277 entries, 174 of them models we track. Switch the scores above to rank them together.
8 models have held number one in labs’ own numbers since its release in March 2024 10 models have held number one across all independent runs since its release in March 2024 16 models have held number one with claims included since its release in March 2024
Lab claims count from the day the card came out, independent runs from the model’s release. We draw one row each for the benchmark’s own leaderboard and what labs claim in their cards.
Sources: Official MMStar leaderboard and labs’ model cards
Qwen’s own number for Qwen 3.8 Max passed 85% in August 2026
That was 29 months after its release. By the same age, 40% of the benchmarks from 2024 had passed 85%. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official MMStar leaderboard and labs’ model cards
4 labs put it in a launch post in the last six months
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Oct 7, 2026 | 80.7 | MMStar | |
| Aug 12, 2026 | LFM2.5-VL-3B | 63.3 | MMStar |
| Aug 12, 2026 | 51.8 | MMStar | |
| Aug 3, 2026 | 85.9 | MMStar | |
| May 25, 2026 | 75.9 | MMStar | |
| Apr 22, 2026 | 81.4 | MMStar | |
| Apr 9, 2026 | 74.9 | MMStar | |
| Apr 2, 2026 | 83.3 | MMStar | |
| Mar 30, 2026 | 79.4 | MMStar | |
| Mar 4, 2026 | 64.5 | MMStar (default mode) | |
| Mar 2, 2026 | 58.3 | MMStar 58.3/55.9 (with CI / without CI) | |
| Mar 2, 2026 | 71.7 | MMStar 71.7/68.0 (with CI / without CI) | |
| Mar 2, 2026 | 78.3 | MMStar | |
| Mar 2, 2026 | 79.7 | MMStar | |
| Feb 24, 2026 | 81.9 | MMStar | |
| Feb 24, 2026 | 81 | MMStar | |
| Feb 24, 2026 | 82.9 | MMStar | |
| Feb 16, 2026 | 83.8 | MMStar | |
| Feb 6, 2026 | 75.5 | MMStar | |
| Jan 13, 2026 | 77.5 | MMStar | |
| Dec 18, 2025 | 79.9 | MMStar | |
| Dec 8, 2025 | GLM-4.6V | 75.9 | MMStar |
| Nov 11, 2025 | 71.1 | MMStar | |
| Oct 31, 2025 | 70.9 | MMStar | |
| Sep 23, 2025 | 78.7 | MMStar | |
| Sep 22, 2025 | 68.5 | MMStar | |
| Aug 25, 2025 | 77.9 | MMStar | |
| Aug 12, 2025 | LFM2-VL-1.6B | 49.5 | MMStar |
| Aug 11, 2025 | GLM-4.5V | 75.3 | MMStar |
| Jul 24, 2025 | 74.9 | MMStar | |
| Jul 1, 2025 | GLM-4.1V-9B-Thinking | 72.9 | MMStar |
| Jun 21, 2025 | Kimi-VL-A3B-Thinking-2506 | 70.4 | MMStar (Acc) |
| May 12, 2025 | 77.8 | MMStar | |
| Mar 27, 2025 | 64 | MMStar | |
| Jan 28, 2025 | 70.8 | MMStar |
22 system cards report it, from 13 labs
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Jun 9, 2026 | | 75.9 | MMStar (Figure 5, printed value) | Capabilities |
| Apr 17, 2026 | | 79.4 | MMStar (Table 6) | Capabilities |
| Apr 9, 2026 | | 74.9 | MMStar (Table 2, Reasoning mode) | Capabilities |
| Mar 21, 2026 | | 79.9 | MMStar (Table 2) | Capabilities |
| Mar 4, 2026 | | 64.5 | MMStar, default mode, 63.9 force nothink and force thinking (Tables 5 and 6) | Capabilities |
| Feb 14, 2026 | | 83 | MMStar (Table 8) | Capabilities |
| Feb 4, 2026 | | 75.5 | MMStar (Table 3) | Capabilities |
| Jan 14, 2026 | | 77.5 | MMStar, SeRe (Tables 1 and 3). PaCoRe 77.64 | Capabilities |
| Jan 1, 2026 | GLM-4.6V technical report | 75.9 | MMStar, GLM-4.6V thinking (Table 2) | Capabilities |
| Nov 28, 2025 | LFM2-VL-1.6B technical report | 49.9 | MMStar, LFM2-VL-1.6B (Table 8) | Capabilities |
| Nov 26, 2025 | | 78.7 | MMStar (Table 2) | Capabilities |
| Nov 6, 2025 | | 71.7 | MMStar, reasoning on (Table 3). Reasoning off 65.9 | Capabilities |
| Oct 31, 2025 | | 70.9 | MMStar (Table 5) | Capabilities |
| Sep 22, 2025 | | 68.5 | MMStar, Instruct (Table 9). Thinking 74.9 (Table 10) | Capabilities |
| Aug 25, 2025 | | 77.9 | MMStar (Table 2, Table 6) | Capabilities |
| Aug 21, 2025 | | 74.9 | MMStar (Table 2) | Capabilities |
| Aug 13, 2025 | GLM-4.5V technical report | 75.3 | MMStar, GLM-4.5V thinking (Table 2) | Capabilities |
| Jul 1, 2025 | GLM-4.1V-9B-Thinking technical report | 72.9 | MMStar, GLM-4.1V-9B-Thinking thinking (Table 2) | Capabilities |
| Jun 23, 2025 | Kimi-VL-A3B-Thinking-2506 technical report | 70.4 | MMStar (Acc) (Table 5) | Capabilities |
| May 11, 2025 | | 77.8 | MMStar, thinking (Table 6). Non-thinking 76.2 | Capabilities |
| Mar 26, 2025 | | 64 | MMStar (Table 5) | Capabilities |
| Feb 19, 2025 | | 70.8 | MMStar (Table 3) | Capabilities |
The lab's number comes out ahead in 2 of 2 pairs that differ
Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. Every benchmark.
| Model | Lab says | Board says | Gap |
|---|---|---|---|
| Kimi-VL-A3B-Thinking-2506 | 70.4% MMStar (Acc) | 70% Leaderboard | +0.4 pts |
| | 70.8% MMStar | 70.5% Leaderboard | +0.3 pts |
More in Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy.
Qwen 3.6 Plus 86%
- MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
- CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
- MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy.
Seed2.1 Pro 90.7%
- MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy.
Qwen 3.8 Max 97.7%
- ChartQA In use Models answer human-written and generated questions about chart images that need visual and arithmetic reasoning. Scored by relaxed accuracy with a 5 percent numeric tolerance.
Command A Vision 90.9%
Data audit
All 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (277 entries), launch posts (35 scores) and system cards (22 scores).
- Pass Models scored 209 models we track, plus 103 other entries on its leaderboard.
- Pass Newest score The newest is from October 2026, for MiniCPM-V-4.7-35B-A3B.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Qwen 3.8 Max (#30).
- Note Headroom Saturated. The best is 85.9%, past 85% since August 2026.
Leaderboard import 3 pass
- Pass Importer We read the board on rank.opencompass.org.cn: 180 rows for models we track and 103 other entries at the last read.
- Pass Last read November 18th, 2026.
- Pass Read worked The last read worked.
Consistency 2 pass
- Pass Lab claims Both pairs agree within 10 points.
- Pass Known issues No published audit found problems.