Unicorn (Vision Safety)
Models answer questions about objects in unusual images and sketches. The benchmark tests how well visual judgments hold up when the images change.
- Made by
- Haoqin Tu and colleagues
- Released
- November 2023
- Kind
- General visual questions
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision
- Strongest model tested
- o3 #84 on the capability index
- Last model added
- April 2025
- Scores refreshed
- November 20th, 2026
Qwen2-VL-72B-Instruct leads with 91.2% among models released by April 2025 Qwen2-VL-72B-Instruct leads with 91.2% among models released by April 2025
Best score per entry from VHELM’s leaderboard, read on November 20th, 2026. VHELM reports prefix quasi-exact match across OODCV-VQA and Sketchy-VQA. Its leaderboard omits their challenge variants. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in April 2025, 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
- 91.2 Qwen2-VL-72B-Instruct
- 90.2 Qwen2-VL-7B-Instruct
- 89.9
Gemini 2.0 Flash
- 89.4
Gemini 1.5 Flash
- 89.0
Gemini 1.5 Pro
- 88.8
Gemini 1.5 Flash
- 88.6
Gemini 2.0 Pro
- 88.3 GPT-4.5
- 88.0
Gemini 2.5 Pro
- 87.9
Gemini 2.0 Flash-Lite
- 87.8
Gemini 1.5 Pro
- 87.5 o4-mini
- 87.2
Qwen2.5-VL-7B
- 87.2 palmyra-vision-003
- 87.0
Qwen2.5-VL-72B
- 87.0 o3
- 86.8 GPT-4o
- 86.3
Gemini 1.0 Pro Vision
- 85.7 GPT-4.1
- 85.6 GPT-4.1 mini
- 85.3 paligemma-3b-mix-224
- 84.8 o1
- 84.5
Llama 4 Scout
- 84.2
Llama 4 Maverick
- 83.0 GPT-4o
- 82.3
PaliGemma-3B-mix-448
- 82.2 GPT-4o mini
- 81.8
Qwen2.5-VL-32B
- 81.5 GPT-4o
- 81.3 GPT-4.1 nano
- 81.2 GPT-4 Turbo
- 80.8
Qwen2.5-VL-3B
- 79.6 GPT-4 Turbo
- 63.5
Pixtral 12B
- 63.0 Claude 3.5 Sonnet (October 2024)
- 62.9
Idefics2-8B
- 62.1 Claude 3.5 Sonnet
- 60.0
IDEFICS-9B-Instruct
- 59.5 Claude 3 Sonnet
- 58.5 Claude 3 Haiku
- 54.0
IDEFICS-80B-Instruct
- 52.5 Claude 3 Opus
- 48.8 Qwen-VL-Chat
- 1 Qwen2-VL-72B-Instruct 91.2%
- 2 Qwen2-VL-7B-Instruct 90.2%
- 3
Gemini 2.0 Flash Feb 2025 89.9%
- 4
Gemini 1.5 Flash Sep 2024 89.4%
- 5
Gemini 1.5 Pro Sep 2024 89%
- 6
Gemini 1.5 Flash May 2024, BLOCK_NONE safety 88.8%
- 7
Gemini 2.0 Pro 88.6%
- 8 GPT-4.5 88.3%
- 9
Gemini 2.5 Pro Mar 2025 88%
- 10
Gemini 2.0 Flash-Lite 87.9%
- 11
Gemini 1.5 Pro May 2024, BLOCK_NONE safety 87.8%
- 12 o4-mini High reasoning effort 87.5%
- 13
Qwen2.5-VL-7B 87.2%
- 14 palmyra-vision-003 87.2%
- 15
Qwen2.5-VL-72B 87%
- 16 o3 High reasoning effort 87%
- 17 GPT-4o Nov 2024 86.8%
- 18
Gemini 1.0 Pro Vision 86.3%
- 19 GPT-4.1 85.7%
- 20 GPT-4.1 mini 85.6%
- 21 paligemma-3b-mix-224 85.3%
- 22 o1 84.8%
- 23
Llama 4 Scout 84.5%
- 24
Llama 4 Maverick 84.2%
- 25 GPT-4o Aug 2024 83%
- 26
PaliGemma-3B-mix-448 82.3%
- 27 GPT-4o mini 82.2%
- 28
Qwen2.5-VL-32B 81.8%
- 29 GPT-4o May 2024 81.5%
- 30 GPT-4.1 nano 81.3%
- 31 GPT-4 Turbo Apr 2024 81.2%
- 32
Qwen2.5-VL-3B 80.8%
- 33 GPT-4 Turbo Nov 2023 79.6%
- 34
Pixtral 12B 63.5%
- 35 Claude 3.5 Sonnet (October 2024) 63%
- 36
Idefics2-8B 62.9%
- 37 Claude 3.5 Sonnet 62.1%
- 38
IDEFICS-9B-Instruct 60%
- 39 Claude 3 Sonnet 59.5%
- 40 Claude 3 Haiku 58.5%
- 41
IDEFICS-80B-Instruct 54%
- 42 Claude 3 Opus 52.5%
- 43 Qwen-VL-Chat 48.8%
Source: VHELM’s leaderboard
- 91.2 Qwen2-VL-72B-Instruct
- 90.2 Qwen2-VL-7B-Instruct
- 89.9
Gemini 2.0 Flash
- 89.4
Gemini 1.5 Flash
- 89.0
Gemini 1.5 Pro
- 88.8
Gemini 1.5 Flash
- 88.6
Gemini 2.0 Pro
- 88.3 GPT-4.5
- 88.0
Gemini 2.5 Pro
- 87.9
Gemini 2.0 Flash-Lite
- 87.8
Gemini 1.5 Pro
- 87.5 o4-mini
- 87.2
Qwen2.5-VL-7B
- 87.0
Qwen2.5-VL-72B
- 87.0 o3
- 86.8 GPT-4o
- 86.3
Gemini 1.0 Pro Vision
- 85.7 GPT-4.1
- 85.6 GPT-4.1 mini
- 84.8 o1
- 84.5
Llama 4 Scout
- 84.2
Llama 4 Maverick
- 83.0 GPT-4o
- 82.3
PaliGemma-3B-mix-448
- 82.2 GPT-4o mini
- 81.8
Qwen2.5-VL-32B
- 81.5 GPT-4o
- 81.3 GPT-4.1 nano
- 81.2 GPT-4 Turbo
- 80.8
Qwen2.5-VL-3B
- 79.6 GPT-4 Turbo
- 63.5
Pixtral 12B
- 63.0 Claude 3.5 Sonnet (October 2024)
- 62.9
Idefics2-8B
- 62.1 Claude 3.5 Sonnet
- 60.0
IDEFICS-9B-Instruct
- 59.5 Claude 3 Sonnet
- 58.5 Claude 3 Haiku
- 54.0
IDEFICS-80B-Instruct
- 52.5 Claude 3 Opus
- 48.8 Qwen-VL-Chat
- 1 Qwen2-VL-72B-Instruct 91.2%
- 2 Qwen2-VL-7B-Instruct 90.2%
- 3
Gemini 2.0 Flash Feb 2025 89.9%
- 4
Gemini 1.5 Flash Sep 2024 89.4%
- 5
Gemini 1.5 Pro Sep 2024 89%
- 6
Gemini 1.5 Flash May 2024, BLOCK_NONE safety 88.8%
- 7
Gemini 2.0 Pro 88.6%
- 8 GPT-4.5 88.3%
- 9
Gemini 2.5 Pro Mar 2025 88%
- 10
Gemini 2.0 Flash-Lite 87.9%
- 11
Gemini 1.5 Pro May 2024, BLOCK_NONE safety 87.8%
- 12 o4-mini High reasoning effort 87.5%
- 13
Qwen2.5-VL-7B 87.2%
- 14
Qwen2.5-VL-72B 87%
- 15 o3 High reasoning effort 87%
- 16 GPT-4o Nov 2024 86.8%
- 17
Gemini 1.0 Pro Vision 86.3%
- 18 GPT-4.1 85.7%
- 19 GPT-4.1 mini 85.6%
- 20 o1 84.8%
- 21
Llama 4 Scout 84.5%
- 22
Llama 4 Maverick 84.2%
- 23 GPT-4o Aug 2024 83%
- 24
PaliGemma-3B-mix-448 82.3%
- 25 GPT-4o mini 82.2%
- 26
Qwen2.5-VL-32B 81.8%
- 27 GPT-4o May 2024 81.5%
- 28 GPT-4.1 nano 81.3%
- 29 GPT-4 Turbo Apr 2024 81.2%
- 30
Qwen2.5-VL-3B 80.8%
- 31 GPT-4 Turbo Nov 2023 79.6%
- 32
Pixtral 12B 63.5%
- 33 Claude 3.5 Sonnet (October 2024) 63%
- 34
Idefics2-8B 62.9%
- 35 Claude 3.5 Sonnet 62.1%
- 36
IDEFICS-9B-Instruct 60%
- 37 Claude 3 Sonnet 59.5%
- 38 Claude 3 Haiku 58.5%
- 39
IDEFICS-80B-Instruct 54%
- 40 Claude 3 Opus 52.5%
- 41 Qwen-VL-Chat 48.8%
Source: VHELM’s leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Qwen2-VL-72B-Instruct | 91.2% | Aug 2024 | Official leaderboard | |
| 2 | Qwen2-VL-7B-Instruct | 90.2% | Aug 2024 | Official leaderboard | |
| 3 | | 89.9% | Feb 2025 | Official leaderboard | |
| 4 | | 89.4% | Aug 2024 | Official leaderboard | |
| 5 | | 89% | Sep 2024 | Official leaderboard | |
| 6 | | 88.8% | BLOCK_NONE safety | May 2024 | Official leaderboard |
| 7 | | 88.6% | Feb 2025 | Official leaderboard | |
| 8 | GPT-4.5 | 88.3% | Feb 2025 | Official leaderboard | |
| 9 | | 88% | Mar 2025 | Official leaderboard | |
| 10 | | 87.9% | Feb 2025 | Official leaderboard | |
| 11 | | 87.8% | BLOCK_NONE safety | May 2024 | Official leaderboard |
| 12 | o4-mini | 87.5% | High reasoning effort | Apr 2025 | Official leaderboard |
| 13 | | 87.2% | Jan 2025 | Official leaderboard | |
| 14 | palmyra-vision-003 | 87.2% | Official leaderboard | ||
| 15 | | 87% | Jan 2025 | Official leaderboard | |
| 16 | o3 | 87% | High reasoning effort | Apr 2025 | Official leaderboard |
| 17 | GPT-4o Nov 2024 | 86.8% | Nov 2024 | Official leaderboard | |
| 18 | | 86.3% | Jan 2024 | Official leaderboard | |
| 19 | GPT-4.1 | 85.7% | Apr 2025 | Official leaderboard | |
| 20 | GPT-4.1 mini | 85.6% | Apr 2025 | Official leaderboard | |
| 21 | paligemma-3b-mix-224 | 85.3% | Official leaderboard | ||
| 22 | o1 | 84.8% | Dec 2024 | Official leaderboard | |
| 23 | | 84.5% | Apr 2025 | Official leaderboard | |
| 24 | | 84.2% | Apr 2025 | Official leaderboard | |
| 25 | GPT-4o Aug 2024 | 83% | Aug 2024 | Official leaderboard | |
| 26 | | 82.3% | May 2024 | Official leaderboard | |
| 27 | GPT-4o mini | 82.2% | Jul 2024 | Official leaderboard | |
| 28 | | 81.8% | Mar 2025 | Official leaderboard | |
| 29 | GPT-4o May 2024 | 81.5% | May 2024 | Official leaderboard | |
| 30 | GPT-4.1 nano | 81.3% | Apr 2025 | Official leaderboard | |
| 31 | GPT-4 Turbo Apr 2024 | 81.2% | Apr 2024 | Official leaderboard | |
| 32 | | 80.8% | Jan 2025 | Official leaderboard | |
| 33 | GPT-4 Turbo Nov 2023 | 79.6% | Nov 2023 | Official leaderboard | |
| 34 | | 63.5% | Sep 2024 | Official leaderboard | |
| 35 | Claude 3.5 Sonnet (October 2024) | 63% | Oct 2024 | Official leaderboard | |
| 36 | | 62.9% | Apr 2024 | Official leaderboard | |
| 37 | Claude 3.5 Sonnet | 62.1% | Jun 2024 | Official leaderboard | |
| 38 | | 60% | Jul 2023 | Official leaderboard | |
| 39 | Claude 3 Sonnet | 59.5% | Feb 2024 | Official leaderboard | |
| 40 | Claude 3 Haiku | 58.5% | Mar 2024 | Official leaderboard | |
| 41 | | 54% | Jul 2023 | Official leaderboard | |
| 42 | Claude 3 Opus | 52.5% | Feb 2024 | Official leaderboard | |
| 43 | Qwen-VL-Chat | 48.8% | Aug 2023 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Qwen2-VL-72B-Instruct | 91.2% | Aug 2024 | Official leaderboard | |
| 2 | Qwen2-VL-7B-Instruct | 90.2% | Aug 2024 | Official leaderboard | |
| 3 | | 89.9% | Feb 2025 | Official leaderboard | |
| 4 | | 89.4% | Aug 2024 | Official leaderboard | |
| 5 | | 89% | Sep 2024 | Official leaderboard | |
| 6 | | 88.8% | BLOCK_NONE safety | May 2024 | Official leaderboard |
| 7 | | 88.6% | Feb 2025 | Official leaderboard | |
| 8 | GPT-4.5 | 88.3% | Feb 2025 | Official leaderboard | |
| 9 | | 88% | Mar 2025 | Official leaderboard | |
| 10 | | 87.9% | Feb 2025 | Official leaderboard | |
| 11 | | 87.8% | BLOCK_NONE safety | May 2024 | Official leaderboard |
| 12 | o4-mini | 87.5% | High reasoning effort | Apr 2025 | Official leaderboard |
| 13 | | 87.2% | Jan 2025 | Official leaderboard | |
| 14 | | 87% | Jan 2025 | Official leaderboard | |
| 15 | o3 | 87% | High reasoning effort | Apr 2025 | Official leaderboard |
| 16 | GPT-4o Nov 2024 | 86.8% | Nov 2024 | Official leaderboard | |
| 17 | | 86.3% | Jan 2024 | Official leaderboard | |
| 18 | GPT-4.1 | 85.7% | Apr 2025 | Official leaderboard | |
| 19 | GPT-4.1 mini | 85.6% | Apr 2025 | Official leaderboard | |
| 20 | o1 | 84.8% | Dec 2024 | Official leaderboard | |
| 21 | | 84.5% | Apr 2025 | Official leaderboard | |
| 22 | | 84.2% | Apr 2025 | Official leaderboard | |
| 23 | GPT-4o Aug 2024 | 83% | Aug 2024 | Official leaderboard | |
| 24 | | 82.3% | May 2024 | Official leaderboard | |
| 25 | GPT-4o mini | 82.2% | Jul 2024 | Official leaderboard | |
| 26 | | 81.8% | Mar 2025 | Official leaderboard | |
| 27 | GPT-4o May 2024 | 81.5% | May 2024 | Official leaderboard | |
| 28 | GPT-4.1 nano | 81.3% | Apr 2025 | Official leaderboard | |
| 29 | GPT-4 Turbo Apr 2024 | 81.2% | Apr 2024 | Official leaderboard | |
| 30 | | 80.8% | Jan 2025 | Official leaderboard | |
| 31 | GPT-4 Turbo Nov 2023 | 79.6% | Nov 2023 | Official leaderboard | |
| 32 | | 63.5% | Sep 2024 | Official leaderboard | |
| 33 | Claude 3.5 Sonnet (October 2024) | 63% | Oct 2024 | Official leaderboard | |
| 34 | | 62.9% | Apr 2024 | Official leaderboard | |
| 35 | Claude 3.5 Sonnet | 62.1% | Jun 2024 | Official leaderboard | |
| 36 | | 60% | Jul 2023 | Official leaderboard | |
| 37 | Claude 3 Sonnet | 59.5% | Feb 2024 | Official leaderboard | |
| 38 | Claude 3 Haiku | 58.5% | Mar 2024 | Official leaderboard | |
| 39 | | 54% | Jul 2023 | Official leaderboard | |
| 40 | Claude 3 Opus | 52.5% | Feb 2024 | Official leaderboard | |
| 41 | Qwen-VL-Chat | 48.8% | Aug 2023 | Official leaderboard |
6 models have held number one on VHELM’s leaderboard since its release in November 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: VHELM’s leaderboard
Gemini 1.0 Pro Vision on the official leaderboard passed 85% in January 2024
That was 2 months after its release. By the same age, 8% of the benchmarks from 2023 had passed 85%. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: VHELM’s 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
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the official leaderboard (43 entries).
- Pass Models scored 41 models we track, plus 2 other entries on its leaderboard.
- Note Newest score The newest came 19 months ago, in April 2025, for o3. That’s expected for a saturated test.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is o3 (#84).
- Note Headroom Saturated. The best is 91.2%, past 85% since January 2024.
Leaderboard import 3 pass
- Pass Importer We read the board on VHELM: 46 rows for models we track and 2 other entries at the last read.
- Pass Last read November 20th, 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.