AGI-Eval Community Image and Video Understanding
Models interpret images and videos. The board reports visual question accuracy and separate comparison win rates.
The 2026/11 leaderboard reports 96 scored model entries on its primary measure.
- Made by
- AGI-Eval (Meituan)
- Released
- February 2025
- Kind
- General visual questions
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- Kept private
- Measures
- Capability
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- A host
- In views
- Vision
- Strongest model tested
- Claude Opus 4.6 #39 on the capability index
- Last model added
- April 2026
- Scores refreshed
- November 21st, 2026
Seed-2.0-Pro-260215 tops the leaderboard with 86.7 Gemini 3 Flash leads with 86.5 among models released by April 2026
Best score per entry from the benchmark's own leaderboard, read on November 21st, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Gemini 3 Flash, at 86.5. This view shows only models we track, each at its best.
The newest model with a score here came out in April 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 86.7 Seed-2.0-Pro-260215
- 86.5
Gemini 3 Flash
- 86.2 Gemini-3-Pro-Preview-Multimodal
- 86.2
Qwen3.5-Plus
- 85.9
Gemini 3.1 Pro
- 84.3 Kimi K2.6
- 82.1
Seed1.8
- 81.8
Qwen3.5-Flash
- 81.7 Kimi K2.5
- 81.1
Seed1.5-VL
- 80.1
Gemini 2.5 Pro
- 79.8
Qwen3-VL-235B-A22B
- 78.3
Gemini 3.1 Flash-Lite
- 78.2 GPT-5
- 77.7 Doubao-Seed-1.6-Thinking-2507
- 77.3 Claude Opus 4.6
- 76.9 GLM-4.6V
- 76.8
Qwen3-VL-235B-A22B-Instruct
- 76.6
Gemini 2.5 Flash
- 76.5 o3
- 76.3 Doubao-Seed-1.6-Thinking-2506
- 75.5 Doubao-Seed-1.6-2506
- 75.1 Claude Sonnet 4.6
- 74.8 Doubao-1.5-Vision-Pro
- 74.5
Qwen3-VL-32B-Instruct
- 73.7 o4-mini
- 73.6 Doubao-Seed-1.6-Flash-250615
- 73.4
Qwen3-VL-32B-Thinking
- 73.3 Doubao-1.5-Vision-Pro-32k-250115
- 71.9 GLM-4.5V
- 71.6 MiMo-VL-7B-RL-2508
- 71.5
Intern-S1
- 71.4 Qwen3-Omni-Flash-2025-1201
- 71.2
Step 3
- 71.0 Kimi-Thinking-Preview
- 70.5
Qwen3-Omni-30B-A3B
- 69.9 Kimi-VL-A3B-Thinking-2506
- 69.6 MiMo-VL-7B-SFT-2508
- 69.5 GLM-4.6V-Flash
- 68.9 GPT-4.1
- 68.8
Gemini 2.0 Pro
- 68.3 GLM-4.1V-9B-Thinking
- 68.0 Doubao-1.5-Vision-Lite-250315
- 67.9 GPT-4.5
- 67.5 Claude Opus 4
- 67.3
Llama 4 Maverick
- 67.3
Qwen3-VL-8B-Thinking
- 67.0
InternVL3.5-241B-A28B
- 67.0
Qwen3-VL-8B-Instruct
- 67.0 MiMo-VL-7B-RL
- 66.8
Gemini 2.0 Flash
- 66.3 MiMo-VL-7B-SFT
- 65.2
InternVL3.5-38B
- 65.0 Claude Sonnet 4
- 64.8
InternVL3-78B
- 64.5 SenseChat-SenseNova-V6-Pro
- 64.3
Skywork-R1V3-38B
- 64.2 GLM-4V
- 63.4 Step-1o-vision-32k
- 62.6 GPT-4o-1120
- 62.5
Qwen2.5-VL-32B
- 62.4 SenseChat-Vision-V5.5
- 61.6
Keye-VL-1.5-8B
- 61.6
Llama 4 Scout
- 61.5 Qwen2.5-72B-VL-Instruct
- 61.4 Doubao-Pro-32k
- 61.4
InternVL3.5-30B-A3B
- 61.1
MiniCPM-V 4.5
- 60.8 Claude 3.7 Sonnet
- 60.5
InternVL3.5-14B
- 59.5 GPT-4o-0513
- 59.2
InternVL3.5-8B
- 59.1 Claude-3.5-Sonnet-1022
- 58.2
Skywork-R1V-38B
- 58.0
InternVL2_5-78B
- 56.8 Keye-VL-8B-Preview-Auto
- 55.9
Keye-VL-8B-Preview
- 55.9 BLIP3o-8B
- 55.0
Gemma 3 27B
- 54.5 InternVL3.5-GPT-OSS-20B-A4B-Preview
- 54.0 Hunyuan-Vision-20250103
- 53.9
BAGEL-7B-MoT
- 53.4
Qwen2.5-VL-7B
- 52.9 Qwen-Omni-Turbo
- 51.1
Gemma 3 12B
- 49.7 Ming-Lite-Omni
- 48.7 Ming-Lite-Omni-1.5
- 45.7 Qwen2.5-Omni-3B
- 42.4
Qwen2.5-Omni-7B
- 41.9 MiniCPM-o-2_6
- 40.0
Gemma 3 4B
- 1 Seed-2.0-Pro-260215 86.7
- 2
Gemini 3 Flash 86.5
- 3 Gemini-3-Pro-Preview-Multimodal 86.2
- 4
Qwen3.5-Plus 86.2
- 5
Gemini 3.1 Pro 85.9
- 6 Kimi K2.6 84.3
- 7
Seed1.8 82.1
- 8
Qwen3.5-Flash 81.8
- 9 Kimi K2.5 81.7
- 10
Seed1.5-VL 81.1
- 11
Gemini 2.5 Pro Jun 2025 80.1
- 12
Qwen3-VL-235B-A22B thinking 79.8
- 13
Gemini 3.1 Flash-Lite 78.3
- 14 GPT-5 78.2
- 15 Doubao-Seed-1.6-Thinking-2507 77.7
- 16 Claude Opus 4.6 77.3
- 17 GLM-4.6V 76.9
- 18
Qwen3-VL-235B-A22B-Instruct 76.8
- 19
Gemini 2.5 Flash Jun 2025, non-thinking 76.6
- 20 o3 76.5
- 21 Doubao-Seed-1.6-Thinking-2506 76.3
- 22 Doubao-Seed-1.6-2506 75.5
- 23 Claude Sonnet 4.6 75.1
- 24 Doubao-1.5-Vision-Pro 74.8
- 25
Qwen3-VL-32B-Instruct 74.5
- 26 o4-mini 73.7
- 27 Doubao-Seed-1.6-Flash-250615 73.6
- 28
Qwen3-VL-32B-Thinking 73.4
- 29 Doubao-1.5-Vision-Pro-32k-250115 73.3
- 30 GLM-4.5V 71.9
- 31 MiMo-VL-7B-RL-2508 nothinking 71.6
- 32
Intern-S1 71.5
- 33 Qwen3-Omni-Flash-2025-1201 71.4
- 34
Step 3 71.2
- 35 Kimi-Thinking-Preview 71.0
- 36
Qwen3-Omni-30B-A3B 70.5
- 37 Kimi-VL-A3B-Thinking-2506 69.9
- 38 MiMo-VL-7B-SFT-2508 69.6
- 39 GLM-4.6V-Flash 69.5
- 40 GPT-4.1 68.9
- 41
Gemini 2.0 Pro 68.8
- 42 GLM-4.1V-9B-Thinking 68.3
- 43 Doubao-1.5-Vision-Lite-250315 68.0
- 44 GPT-4.5 67.9
- 45 Claude Opus 4 67.5
- 46
Llama 4 Maverick 67.3
- 47
Qwen3-VL-8B-Thinking 67.3
- 48
InternVL3.5-241B-A28B 67.0
- 49
Qwen3-VL-8B-Instruct 67.0
- 50 MiMo-VL-7B-RL 67.0
- 51
Gemini 2.0 Flash Feb 2025 66.8
- 52 MiMo-VL-7B-SFT 66.3
- 53
InternVL3.5-38B 65.2
- 54 Claude Sonnet 4 65.0
- 55
InternVL3-78B 64.8
- 56 SenseChat-SenseNova-V6-Pro 64.5
- 57
Skywork-R1V3-38B 64.3
- 58 GLM-4V 64.2
- 59 Step-1o-vision-32k 63.4
- 60 GPT-4o-1120 62.6
- 61
Qwen2.5-VL-32B 62.5
- 62 SenseChat-Vision-V5.5 62.4
- 63
Keye-VL-1.5-8B thinking 61.6
- 64
Llama 4 Scout 61.6
- 65 Qwen2.5-72B-VL-Instruct 61.5
- 66 Doubao-Pro-32k 61.4
- 67
InternVL3.5-30B-A3B 61.4
- 68
MiniCPM-V 4.5 61.1
- 69 Claude 3.7 Sonnet 60.8
- 70
InternVL3.5-14B 60.5
- 71 GPT-4o-0513 59.5
- 72
InternVL3.5-8B 59.2
- 73 Claude-3.5-Sonnet-1022 59.1
- 74
Skywork-R1V-38B 58.2
- 75
InternVL2_5-78B 58.0
- 76 Keye-VL-8B-Preview-Auto 56.8
- 77
Keye-VL-8B-Preview thinking 55.9
- 78 BLIP3o-8B 55.9
- 79
Gemma 3 27B 55.0
- 80 InternVL3.5-GPT-OSS-20B-A4B-Preview 54.5
- 81 Hunyuan-Vision-20250103 54.0
- 82
BAGEL-7B-MoT 53.9
- 83
Qwen2.5-VL-7B 53.4
- 84 Qwen-Omni-Turbo 52.9
- 85
Gemma 3 12B 51.1
- 86 Ming-Lite-Omni 49.7
- 87 Ming-Lite-Omni-1.5 48.7
- 88 Qwen2.5-Omni-3B 45.7
- 89
Qwen2.5-Omni-7B 42.4
- 90 MiniCPM-o-2_6 41.9
- 91
Gemma 3 4B 40.0
Source: Official AGI-Eval Community Image and Video Understanding leaderboard
- 86.5
Gemini 3 Flash
- 86.2
Qwen3.5-Plus
- 85.9
Gemini 3.1 Pro
- 84.3 Kimi K2.6
- 82.1
Seed1.8
- 81.8
Qwen3.5-Flash
- 81.7 Kimi K2.5
- 81.1
Seed1.5-VL
- 80.1
Gemini 2.5 Pro
- 79.8
Qwen3-VL-235B-A22B
- 78.3
Gemini 3.1 Flash-Lite
- 78.2 GPT-5
- 77.3 Claude Opus 4.6
- 76.9 GLM-4.6V
- 76.8
Qwen3-VL-235B-A22B-Instruct
- 76.6
Gemini 2.5 Flash
- 76.5 o3
- 75.1 Claude Sonnet 4.6
- 74.5
Qwen3-VL-32B-Instruct
- 73.7 o4-mini
- 73.4
Qwen3-VL-32B-Thinking
- 71.9 GLM-4.5V
- 71.6 MiMo-VL-7B-RL-2508
- 71.5
Intern-S1
- 71.2
Step 3
- 70.5
Qwen3-Omni-30B-A3B
- 69.9 Kimi-VL-A3B-Thinking-2506
- 69.6 MiMo-VL-7B-SFT-2508
- 69.5 GLM-4.6V-Flash
- 68.9 GPT-4.1
- 68.8
Gemini 2.0 Pro
- 68.3 GLM-4.1V-9B-Thinking
- 67.9 GPT-4.5
- 67.5 Claude Opus 4
- 67.3
Llama 4 Maverick
- 67.3
Qwen3-VL-8B-Thinking
- 67.0
InternVL3.5-241B-A28B
- 67.0
Qwen3-VL-8B-Instruct
- 67.0 MiMo-VL-7B-RL
- 66.8
Gemini 2.0 Flash
- 66.3 MiMo-VL-7B-SFT
- 65.2
InternVL3.5-38B
- 65.0 Claude Sonnet 4
- 64.8
InternVL3-78B
- 64.3
Skywork-R1V3-38B
- 62.5
Qwen2.5-VL-32B
- 61.6
Keye-VL-1.5-8B
- 61.6
Llama 4 Scout
- 61.4
InternVL3.5-30B-A3B
- 61.1
MiniCPM-V 4.5
- 60.8 Claude 3.7 Sonnet
- 60.5
InternVL3.5-14B
- 59.2
InternVL3.5-8B
- 58.2
Skywork-R1V-38B
- 58.0
InternVL2_5-78B
- 55.9
Keye-VL-8B-Preview
- 55.0
Gemma 3 27B
- 53.9
BAGEL-7B-MoT
- 53.4
Qwen2.5-VL-7B
- 51.1
Gemma 3 12B
- 42.4
Qwen2.5-Omni-7B
- 41.9 MiniCPM-o-2_6
- 40.0
Gemma 3 4B
- 1
Gemini 3 Flash 86.5
- 2
Qwen3.5-Plus 86.2
- 3
Gemini 3.1 Pro 85.9
- 4 Kimi K2.6 84.3
- 5
Seed1.8 82.1
- 6
Qwen3.5-Flash 81.8
- 7 Kimi K2.5 81.7
- 8
Seed1.5-VL 81.1
- 9
Gemini 2.5 Pro Jun 2025 80.1
- 10
Qwen3-VL-235B-A22B thinking 79.8
- 11
Gemini 3.1 Flash-Lite 78.3
- 12 GPT-5 78.2
- 13 Claude Opus 4.6 77.3
- 14 GLM-4.6V 76.9
- 15
Qwen3-VL-235B-A22B-Instruct 76.8
- 16
Gemini 2.5 Flash Jun 2025, non-thinking 76.6
- 17 o3 76.5
- 18 Claude Sonnet 4.6 75.1
- 19
Qwen3-VL-32B-Instruct 74.5
- 20 o4-mini 73.7
- 21
Qwen3-VL-32B-Thinking 73.4
- 22 GLM-4.5V 71.9
- 23 MiMo-VL-7B-RL-2508 nothinking 71.6
- 24
Intern-S1 71.5
- 25
Step 3 71.2
- 26
Qwen3-Omni-30B-A3B 70.5
- 27 Kimi-VL-A3B-Thinking-2506 69.9
- 28 MiMo-VL-7B-SFT-2508 69.6
- 29 GLM-4.6V-Flash 69.5
- 30 GPT-4.1 68.9
- 31
Gemini 2.0 Pro 68.8
- 32 GLM-4.1V-9B-Thinking 68.3
- 33 GPT-4.5 67.9
- 34 Claude Opus 4 67.5
- 35
Llama 4 Maverick 67.3
- 36
Qwen3-VL-8B-Thinking 67.3
- 37
InternVL3.5-241B-A28B 67.0
- 38
Qwen3-VL-8B-Instruct 67.0
- 39 MiMo-VL-7B-RL 67.0
- 40
Gemini 2.0 Flash Feb 2025 66.8
- 41 MiMo-VL-7B-SFT 66.3
- 42
InternVL3.5-38B 65.2
- 43 Claude Sonnet 4 65.0
- 44
InternVL3-78B 64.8
- 45
Skywork-R1V3-38B 64.3
- 46
Qwen2.5-VL-32B 62.5
- 47
Keye-VL-1.5-8B thinking 61.6
- 48
Llama 4 Scout 61.6
- 49
InternVL3.5-30B-A3B 61.4
- 50
MiniCPM-V 4.5 61.1
- 51 Claude 3.7 Sonnet 60.8
- 52
InternVL3.5-14B 60.5
- 53
InternVL3.5-8B 59.2
- 54
Skywork-R1V-38B 58.2
- 55
InternVL2_5-78B 58.0
- 56
Keye-VL-8B-Preview thinking 55.9
- 57
Gemma 3 27B 55.0
- 58
BAGEL-7B-MoT 53.9
- 59
Qwen2.5-VL-7B 53.4
- 60
Gemma 3 12B 51.1
- 61
Qwen2.5-Omni-7B 42.4
- 62 MiniCPM-o-2_6 41.9
- 63
Gemma 3 4B 40.0
Source: Official AGI-Eval Community Image and Video Understanding leaderboard
| # | Entry | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | Seed-2.0-Pro-260215 | 86.7 | Mar 2026 | Official leaderboard | ||
| 2 | | 86.5 | Dec 2025 | Dec 2025 | Official leaderboard | |
| 3 | Gemini-3-Pro-Preview-Multimodal | 86.2 | Dec 2025 | Official leaderboard | ||
| 4 | | 86.2 | Feb 2026 | Mar 2026 | Official leaderboard | |
| 5 | | 85.9 | Feb 2026 | Mar 2026 | Official leaderboard | |
| 6 | Kimi K2.6 | 84.3 | Apr 2026 | Jun 2026 | Official leaderboard | |
| 7 | | 82.1 | Dec 2025 | Jan 2026 | Official leaderboard | |
| 8 | | 81.8 | Feb 2026 | Mar 2026 | Official leaderboard | |
| 9 | Kimi K2.5 | 81.7 | Jan 2026 | Feb 2026 | Official leaderboard | |
| 10 | | 81.1 | May 2025 | Aug 2025 | Official leaderboard | |
| 11 | | 80.1 | Jun 2025 | Jul 2025 | Official leaderboard | |
| 12 | | 79.8 | thinking | Sep 2025 | Nov 2025 | Official leaderboard |
| 13 | | 78.3 | Mar 2026 | Mar 2026 | Official leaderboard | |
| 14 | GPT-5 | 78.2 | Aug 2025 | Sep 2025 | Official leaderboard | |
| 15 | Doubao-Seed-1.6-Thinking-2507 | 77.7 | Sep 2025 | Official leaderboard | ||
| 16 | Claude Opus 4.6 | 77.3 | Feb 2026 | Mar 2026 | Official leaderboard | |
| 17 | GLM-4.6V | 76.9 | Dec 2025 | Jan 2026 | Official leaderboard | |
| 18 | | 76.8 | Sep 2025 | Nov 2025 | Official leaderboard | |
| 19 | | 76.6 | non-thinking | Jun 2025 | Sep 2025 | Official leaderboard |
| 20 | o3 | 76.5 | Apr 2025 | Mar 2026 | Official leaderboard | |
| 21 | Doubao-Seed-1.6-Thinking-2506 | 76.3 | Sep 2025 | Official leaderboard | ||
| 22 | Doubao-Seed-1.6-2506 | 75.5 | Aug 2025 | Official leaderboard | ||
| 23 | Claude Sonnet 4.6 | 75.1 | Feb 2026 | Mar 2026 | Official leaderboard | |
| 24 | Doubao-1.5-Vision-Pro | 74.8 | Aug 2025 | Official leaderboard | ||
| 25 | | 74.5 | Oct 2025 | Dec 2025 | Official leaderboard | |
| 26 | o4-mini | 73.7 | Apr 2025 | Mar 2026 | Official leaderboard | |
| 27 | Doubao-Seed-1.6-Flash-250615 | 73.6 | Nov 2026 | Official leaderboard | ||
| 28 | | 73.4 | Oct 2025 | Dec 2025 | Official leaderboard | |
| 29 | Doubao-1.5-Vision-Pro-32k-250115 | 73.3 | Nov 2026 | Official leaderboard | ||
| 30 | GLM-4.5V | 71.9 | Aug 2025 | Aug 2025 | Official leaderboard | |
| 31 | MiMo-VL-7B-RL-2508 | 71.6 | nothinking | Aug 2025 | Sep 2025 | Official leaderboard |
| 32 | | 71.5 | Jul 2025 | Sep 2025 | Official leaderboard | |
| 33 | Qwen3-Omni-Flash-2025-1201 | 71.4 | Dec 2025 | Official leaderboard | ||
| 34 | | 71.2 | Jul 2025 | Aug 2025 | Official leaderboard | |
| 35 | Kimi-Thinking-Preview | 71.0 | Sep 2025 | Official leaderboard | ||
| 36 | | 70.5 | Sep 2025 | Mar 2026 | Official leaderboard | |
| 37 | Kimi-VL-A3B-Thinking-2506 | 69.9 | Jun 2025 | Sep 2025 | Official leaderboard | |
| 38 | MiMo-VL-7B-SFT-2508 | 69.6 | Aug 2025 | Sep 2025 | Official leaderboard | |
| 39 | GLM-4.6V-Flash | 69.5 | Dec 2025 | Jan 2026 | Official leaderboard | |
| 40 | GPT-4.1 | 68.9 | Apr 2025 | Sep 2025 | Official leaderboard | |
| 41 | | 68.8 | Feb 2025 | Sep 2025 | Official leaderboard | |
| 42 | GLM-4.1V-9B-Thinking | 68.3 | Jul 2025 | Apr 2026 | Official leaderboard | |
| 43 | Doubao-1.5-Vision-Lite-250315 | 68.0 | Nov 2026 | Official leaderboard | ||
| 44 | GPT-4.5 | 67.9 | Feb 2025 | Jul 2025 | Official leaderboard | |
| 45 | Claude Opus 4 | 67.5 | May 2025 | Aug 2025 | Official leaderboard | |
| 46 | | 67.3 | Apr 2025 | Mar 2026 | Official leaderboard | |
| 47 | | 67.3 | Oct 2025 | Dec 2025 | Official leaderboard | |
| 48 | | 67.0 | Aug 2025 | Sep 2025 | Official leaderboard | |
| 49 | | 67.0 | Oct 2025 | Dec 2025 | Official leaderboard | |
| 50 | MiMo-VL-7B-RL | 67.0 | May 2025 | Aug 2025 | Official leaderboard | |
| 51 | | 66.8 | Feb 2025 | Jun 2025 | Official leaderboard | |
| 52 | MiMo-VL-7B-SFT | 66.3 | May 2025 | Nov 2026 | Official leaderboard | |
| 53 | | 65.2 | Aug 2025 | Sep 2025 | Official leaderboard | |
| 54 | Claude Sonnet 4 | 65.0 | May 2025 | Sep 2025 | Official leaderboard | |
| 55 | | 64.8 | Apr 2025 | Nov 2026 | Official leaderboard | |
| 56 | SenseChat-SenseNova-V6-Pro | 64.5 | Nov 2026 | Official leaderboard | ||
| 57 | | 64.3 | Jul 2025 | Aug 2025 | Official leaderboard | |
| 58 | GLM-4V | 64.2 | May 2025 | Official leaderboard | ||
| 59 | Step-1o-vision-32k | 63.4 | Nov 2026 | Official leaderboard | ||
| 60 | GPT-4o-1120 | 62.6 | Mar 2026 | Official leaderboard | ||
| 61 | | 62.5 | Mar 2025 | Sep 2025 | Official leaderboard | |
| 62 | SenseChat-Vision-V5.5 | 62.4 | Jun 2025 | Official leaderboard | ||
| 63 | | 61.6 | thinking | Aug 2025 | Sep 2025 | Official leaderboard |
| 64 | | 61.6 | Apr 2025 | Mar 2026 | Official leaderboard | |
| 65 | Qwen2.5-72B-VL-Instruct | 61.5 | Nov 2026 | Official leaderboard | ||
| 66 | Doubao-Pro-32k | 61.4 | Nov 2026 | Official leaderboard | ||
| 67 | | 61.4 | Aug 2025 | Sep 2025 | Official leaderboard | |
| 68 | | 61.1 | Aug 2025 | Sep 2025 | Official leaderboard | |
| 69 | Claude 3.7 Sonnet | 60.8 | Feb 2025 | Mar 2026 | Official leaderboard | |
| 70 | | 60.5 | Aug 2025 | Sep 2025 | Official leaderboard | |
| 71 | GPT-4o-0513 | 59.5 | Jan 2026 | Official leaderboard | ||
| 72 | | 59.2 | Aug 2025 | Sep 2025 | Official leaderboard | |
| 73 | Claude-3.5-Sonnet-1022 | 59.1 | Mar 2026 | Official leaderboard | ||
| 74 | | 58.2 | Mar 2025 | May 2025 | Official leaderboard | |
| 75 | | 58.0 | Dec 2024 | Nov 2026 | Official leaderboard | |
| 76 | Keye-VL-8B-Preview-Auto | 56.8 | Aug 2025 | Official leaderboard | ||
| 77 | | 55.9 | thinking | Jun 2025 | Aug 2025 | Official leaderboard |
| 78 | BLIP3o-8B | 55.9 | Sep 2025 | Official leaderboard | ||
| 79 | | 55.0 | Mar 2025 | Mar 2026 | Official leaderboard | |
| 80 | InternVL3.5-GPT-OSS-20B-A4B-Preview | 54.5 | Sep 2025 | Official leaderboard | ||
| 81 | Hunyuan-Vision-20250103 | 54.0 | May 2025 | Official leaderboard | ||
| 82 | | 53.9 | May 2025 | Aug 2025 | Official leaderboard | |
| 83 | | 53.4 | Jan 2025 | Nov 2026 | Official leaderboard | |
| 84 | Qwen-Omni-Turbo | 52.9 | May 2025 | Official leaderboard | ||
| 85 | | 51.1 | Mar 2025 | Mar 2026 | Official leaderboard | |
| 86 | Ming-Lite-Omni | 49.7 | Aug 2025 | Official leaderboard | ||
| 87 | Ming-Lite-Omni-1.5 | 48.7 | Aug 2025 | Official leaderboard | ||
| 88 | Qwen2.5-Omni-3B | 45.7 | Aug 2025 | Official leaderboard | ||
| 89 | | 42.4 | Mar 2025 | Sep 2025 | Official leaderboard | |
| 90 | MiniCPM-o-2_6 | 41.9 | Jan 2025 | May 2025 | Official leaderboard | |
| 91 | | 40.0 | Mar 2025 | Feb 2026 | Official leaderboard |
| # | Model | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | | 86.5 | Dec 2025 | Dec 2025 | Official leaderboard | |
| 2 | | 86.2 | Feb 2026 | Mar 2026 | Official leaderboard | |
| 3 | | 85.9 | Feb 2026 | Mar 2026 | Official leaderboard | |
| 4 | Kimi K2.6 | 84.3 | Apr 2026 | Jun 2026 | Official leaderboard | |
| 5 | | 82.1 | Dec 2025 | Jan 2026 | Official leaderboard | |
| 6 | | 81.8 | Feb 2026 | Mar 2026 | Official leaderboard | |
| 7 | Kimi K2.5 | 81.7 | Jan 2026 | Feb 2026 | Official leaderboard | |
| 8 | | 81.1 | May 2025 | Aug 2025 | Official leaderboard | |
| 9 | | 80.1 | Jun 2025 | Jul 2025 | Official leaderboard | |
| 10 | | 79.8 | thinking | Sep 2025 | Nov 2025 | Official leaderboard |
| 11 | | 78.3 | Mar 2026 | Mar 2026 | Official leaderboard | |
| 12 | GPT-5 | 78.2 | Aug 2025 | Sep 2025 | Official leaderboard | |
| 13 | Claude Opus 4.6 | 77.3 | Feb 2026 | Mar 2026 | Official leaderboard | |
| 14 | GLM-4.6V | 76.9 | Dec 2025 | Jan 2026 | Official leaderboard | |
| 15 | | 76.8 | Sep 2025 | Nov 2025 | Official leaderboard | |
| 16 | | 76.6 | non-thinking | Jun 2025 | Sep 2025 | Official leaderboard |
| 17 | o3 | 76.5 | Apr 2025 | Mar 2026 | Official leaderboard | |
| 18 | Claude Sonnet 4.6 | 75.1 | Feb 2026 | Mar 2026 | Official leaderboard | |
| 19 | | 74.5 | Oct 2025 | Dec 2025 | Official leaderboard | |
| 20 | o4-mini | 73.7 | Apr 2025 | Mar 2026 | Official leaderboard | |
| 21 | | 73.4 | Oct 2025 | Dec 2025 | Official leaderboard | |
| 22 | GLM-4.5V | 71.9 | Aug 2025 | Aug 2025 | Official leaderboard | |
| 23 | MiMo-VL-7B-RL-2508 | 71.6 | nothinking | Aug 2025 | Sep 2025 | Official leaderboard |
| 24 | | 71.5 | Jul 2025 | Sep 2025 | Official leaderboard | |
| 25 | | 71.2 | Jul 2025 | Aug 2025 | Official leaderboard | |
| 26 | | 70.5 | Sep 2025 | Mar 2026 | Official leaderboard | |
| 27 | Kimi-VL-A3B-Thinking-2506 | 69.9 | Jun 2025 | Sep 2025 | Official leaderboard | |
| 28 | MiMo-VL-7B-SFT-2508 | 69.6 | Aug 2025 | Sep 2025 | Official leaderboard | |
| 29 | GLM-4.6V-Flash | 69.5 | Dec 2025 | Jan 2026 | Official leaderboard | |
| 30 | GPT-4.1 | 68.9 | Apr 2025 | Sep 2025 | Official leaderboard | |
| 31 | | 68.8 | Feb 2025 | Sep 2025 | Official leaderboard | |
| 32 | GLM-4.1V-9B-Thinking | 68.3 | Jul 2025 | Apr 2026 | Official leaderboard | |
| 33 | GPT-4.5 | 67.9 | Feb 2025 | Jul 2025 | Official leaderboard | |
| 34 | Claude Opus 4 | 67.5 | May 2025 | Aug 2025 | Official leaderboard | |
| 35 | | 67.3 | Apr 2025 | Mar 2026 | Official leaderboard | |
| 36 | | 67.3 | Oct 2025 | Dec 2025 | Official leaderboard | |
| 37 | | 67.0 | Aug 2025 | Sep 2025 | Official leaderboard | |
| 38 | | 67.0 | Oct 2025 | Dec 2025 | Official leaderboard | |
| 39 | MiMo-VL-7B-RL | 67.0 | May 2025 | Aug 2025 | Official leaderboard | |
| 40 | | 66.8 | Feb 2025 | Jun 2025 | Official leaderboard | |
| 41 | MiMo-VL-7B-SFT | 66.3 | May 2025 | Nov 2026 | Official leaderboard | |
| 42 | | 65.2 | Aug 2025 | Sep 2025 | Official leaderboard | |
| 43 | Claude Sonnet 4 | 65.0 | May 2025 | Sep 2025 | Official leaderboard | |
| 44 | | 64.8 | Apr 2025 | Nov 2026 | Official leaderboard | |
| 45 | | 64.3 | Jul 2025 | Aug 2025 | Official leaderboard | |
| 46 | | 62.5 | Mar 2025 | Sep 2025 | Official leaderboard | |
| 47 | | 61.6 | thinking | Aug 2025 | Sep 2025 | Official leaderboard |
| 48 | | 61.6 | Apr 2025 | Mar 2026 | Official leaderboard | |
| 49 | | 61.4 | Aug 2025 | Sep 2025 | Official leaderboard | |
| 50 | | 61.1 | Aug 2025 | Sep 2025 | Official leaderboard | |
| 51 | Claude 3.7 Sonnet | 60.8 | Feb 2025 | Mar 2026 | Official leaderboard | |
| 52 | | 60.5 | Aug 2025 | Sep 2025 | Official leaderboard | |
| 53 | | 59.2 | Aug 2025 | Sep 2025 | Official leaderboard | |
| 54 | | 58.2 | Mar 2025 | May 2025 | Official leaderboard | |
| 55 | | 58.0 | Dec 2024 | Nov 2026 | Official leaderboard | |
| 56 | | 55.9 | thinking | Jun 2025 | Aug 2025 | Official leaderboard |
| 57 | | 55.0 | Mar 2025 | Mar 2026 | Official leaderboard | |
| 58 | | 53.9 | May 2025 | Aug 2025 | Official leaderboard | |
| 59 | | 53.4 | Jan 2025 | Nov 2026 | Official leaderboard | |
| 60 | | 51.1 | Mar 2025 | Mar 2026 | Official leaderboard | |
| 61 | | 42.4 | Mar 2025 | Sep 2025 | Official leaderboard | |
| 62 | MiniCPM-o-2_6 | 41.9 | Jan 2025 | May 2025 | Official leaderboard | |
| 63 | | 40.0 | Mar 2025 | Feb 2026 | Official leaderboard |
Rankings by part
We read 11 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Image to text objective accuracy, Multi-image understanding and Character information recognition. Qwen3.5-Plus leads 5 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
Image to text objective accuracy
63 models we track have a score here.
- 1
Gemini 3 Flash 86.5
- 2
Qwen3.5-Plus 86.2
- 3
Gemini 3.1 Pro 85.9
- 4 Kimi K2.6 84.3
- 5
Seed1.8 82.1
- 6
Qwen3.5-Flash 81.8
- 7 Kimi K2.5 81.7
- 8
Seed1.5-VL 81.1
- 9
Gemini 2.5 Pro Jun 2025 80.1
- 10
Qwen3-VL-235B-A22B 79.8
Multi-image understanding
61 models we track have a score here.
- 1
Gemini 3.1 Pro ↑2 85.3
- 2
Qwen3.5-Plus 84.5
- 3
Gemini 3 Flash ↓2 83.9
- 4 GPT-5 ↑8 81.4
- 5
Gemini 3.1 Flash-Lite ↑6 80.9
- 6
Qwen3.5-Flash 80.9
- 7 o3 ↑10 80.9
- 8
Gemini 2.5 Pro Jun 2025 ↑1 79.5
- 9
Seed1.8 ↓4 78.6
- 10
Seed1.5-VL ↓2 78.4
Character information recognition
61 models we track have a score here.
- 1
Qwen3.5-Plus ↑1 92.6
- 2
Gemini 3.1 Pro ↑1 90.5
- 3
Qwen3-VL-235B-A22B ↑7 90.0
- 4
Gemini 3 Flash ↓3 89.9
- 5
Qwen3.5-Flash ↑1 89.2
- 6
Qwen3-VL-235B-A22B-Instruct ↑9 88.9
- 7
Qwen3-VL-32B-Instruct ↑12 88.5
- 8
Seed1.8 ↓3 87.3
- 9
Qwen3-VL-8B-Instruct ↑29 86.8
- 10
Seed1.5-VL ↓2 86.1
Academic reasoning
61 models we track have a score here.
- 1
Gemini 3.1 Pro ↑2 84.1
- 2
Gemini 3 Flash ↓1 83.2
- 3
Qwen3.5-Plus ↓1 81.8
- 4
Qwen3.5-Flash ↑2 77.5
- 5 Kimi K2.5 ↑2 76.3
- 6
Seed1.8 ↓1 76.0
- 7 GPT-5 ↑5 74.5
- 8
Gemini 2.5 Pro Jun 2025 ↑1 74.5
- 9
Seed1.5-VL ↓1 73.7
- 10 Claude Opus 4.6 ↑3 73.7
Entity attribute recognition
61 models we track have a score here.
- 1
Qwen3.5-Plus ↑1 87.0
- 2
Gemini 3.1 Pro ↑1 86.7
- 3
Gemini 3 Flash ↓2 86.5
- 4
Qwen3.5-Flash ↑2 85.2
- 5 Kimi K2.5 ↑2 84.7
- 6
Seed1.5-VL ↑2 84.7
- 7
Gemini 2.5 Pro Jun 2025 ↑2 84.6
- 8
Seed1.8 ↓3 84.0
- 9 GPT-5 ↑3 83.8
- 10 o3 ↑7 83.8
Entity recognition
61 models we track have a score here.
- 1
Qwen3.5-Plus ↑1 87.3
- 2
Gemini 3.1 Pro ↑1 87.2
- 3
Gemini 3 Flash ↓2 87.0
- 4
Seed1.5-VL ↑4 85.8
- 5 Kimi K2.5 ↑2 85.6
- 6
Gemini 2.5 Pro Jun 2025 ↑3 85.6
- 7
Qwen3.5-Flash ↓1 85.4
- 8
Seed1.8 ↓3 84.4
- 9
Qwen3-VL-32B-Thinking ↑12 84.2
- 10
Gemini 3.1 Flash-Lite ↑1 84.2
Perception
61 models we track have a score here.
- 1
Qwen3.5-Plus ↑1 88.0
- 2
Gemini 3.1 Pro ↑1 87.6
- 3
Gemini 3 Flash ↓2 87.2
- 4
Qwen3.5-Flash ↑2 85.8
- 5
Seed1.8 84.8
- 6 Kimi K2.5 ↑1 84.1
- 7
Qwen3-VL-235B-A22B-Instruct ↑8 83.8
- 8
Seed1.5-VL 83.7
- 9
Qwen3-VL-235B-A22B ↑1 83.7
- 10 GPT-5 ↑2 83.6
Reasoning
61 models we track have a score here.
- 1
Gemini 3 Flash 86.1
- 2
Qwen3.5-Plus 85.2
- 3
Gemini 3.1 Pro 85.1
- 4
Seed1.8 ↑1 80.7
- 5 Kimi K2.5 ↑2 80.5
- 6
Seed1.5-VL ↑2 79.8
- 7
Qwen3.5-Flash ↓1 79.7
- 8
Gemini 2.5 Pro Jun 2025 ↑1 79.1
- 9
Qwen3-VL-235B-A22B ↑1 77.9
- 10
Gemini 3.1 Flash-Lite ↑1 75.7
Overall attribute recognition
61 models we track have a score here.
- 1
Gemini 3.1 Pro ↑2 89.2
- 2 GPT-5 ↑10 87.8
- 3
Qwen3.5-Plus ↓1 87.5
- 4
Gemini 3 Flash ↓3 87.2
- 5 o3 ↑12 86.9
- 6
Qwen3.5-Flash 86.0
- 7 Claude Opus 4.6 ↑6 85.8
- 8
Gemini 3.1 Flash-Lite ↑3 85.4
- 9
Seed1.8 ↓4 85.4
- 10 o4-mini ↑10 84.9
Knowledge
61 models we track have a score here.
- 1
Gemini 3 Flash 91.1
- 2
Gemini 3.1 Pro ↑1 90.6
- 3
Qwen3.5-Plus ↓1 89.2
- 4
Seed1.8 ↑1 88.1
- 5
Seed1.5-VL ↑3 87.2
- 6
Gemini 2.5 Pro Jun 2025 ↑3 85.3
- 7
Qwen3.5-Flash ↓1 84.5
- 8
Gemini 3.1 Flash-Lite ↑3 84.3
- 9
Qwen3-VL-235B-A22B ↑1 83.4
- 10 Kimi K2.5 ↓3 82.8
General reasoning
61 models we track have a score here.
- 1
Qwen3.5-Plus ↑1 87.8
- 2
Gemini 3 Flash ↓1 87.5
- 3 Kimi K2.5 ↑4 85.0
- 4
Seed1.5-VL ↑4 84.1
- 5
Gemini 3.1 Pro ↓2 83.5
- 6
Seed1.8 ↓1 83.4
- 7
Gemini 2.5 Pro Jun 2025 ↑2 82.2
- 8
Qwen3-VL-235B-A22B ↑2 82.0
- 9 GLM-4.6V ↑5 80.3
- 10
Qwen3.5-Flash ↓4 80.1
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official AGI-Eval Community Image and Video Understanding leaderboard
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official AGI-Eval Community Image and Video Understanding leaderboard
6 models have held number one on the official leaderboard since its release in February 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official AGI-Eval Community Image and Video Understanding leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official AGI-Eval Community Image and Video Understanding leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
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%
- MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy.
Qwen 3.8 Max 85.9%
Data audit
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 7 months ago, in April 2026, for Kimi K2.6. Every benchmark
Catalog record 2 pass
- Pass Task access The tasks are private.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (91 entries).
- Pass Models scored 63 models we track, plus 28 other entries on its leaderboard.
- Warning Newest score The newest came 7 months ago, in April 2026, for Kimi K2.6.
- Note Frontier models None of the top 10 has a score. The strongest tested is Claude Opus 4.6 (#39).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on agi-eval.org: 68 rows for models we track and 28 other entries at the last read.
- Pass Last read November 21st, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.