WTP-Bench
Models identify Pokémon from official artwork and silhouettes across 1,160 entries. The scorer checks exact forms, species, and evolutionary families.
The maker publishes four accuracy measures for 27 vision models. The silhouette column measures exact form matches.
- Released
- February 2026
- Kind
- General visual questions
- Level
- School
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision
- Strongest model tested
- Claude Sonnet 4.5 #81 on the capability index
- Last model added
- October 2025
- Scores refreshed
- November 20th, 2026
GPT-4.1 leads with 79% among models released by October 2025 GPT-4.1 leads with 79% among models released by October 2025
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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 October 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
- 79.0 GPT-4.1
- 78.2
Gemini 2.5 Pro
- 77.2
Gemini 2.5 Flash
- 65.1 Claude Sonnet 4.5
- 49.3 GPT-4o mini
- 46.9 Grok 4 Fast
- 27.6 Claude Haiku 4.5
- 13.4
Qwen3-VL-4B-Instruct
- 12.8 Qwen3-VL 8B
- 7.16
Pixtral 12B
- 6.47 Qwen2-VL-7B-Instruct
- 5.95
Ovis2.5-9B
- 4.14
InternVL2.5-26B
- 3.53
LLaVA-OneVision 7B
- 3.53
Qwen2.5-VL-7B
- 2.93 Florence-VL 8B
- 2.84
Qwen2.5-VL-3B
- 2.76
Ovis2.5-2B
- 2.24
Qwen2-VL-2B-Instruct
- 2.24
SmolVLM-Instruct
- 1.98
PaliGemma-3B-mix-448
- 1.81 PaliGemma 3B
- 1.81
LLaVA-v1.5-13B
- 1.03 llava-v1.5-7b
- 0.86
InternVL2-8B
- 0.17
Phi-3-vision-128k-instruct
- 0.09
InternVL2-1B
- 1 GPT-4.1 79%
- 2
Gemini 2.5 Pro Jun 2025 78.2%
- 3
Gemini 2.5 Flash Sep 2025 77.2%
- 4 Claude Sonnet 4.5 65.1%
- 5 GPT-4o mini 49.3%
- 6 Grok 4 Fast 46.9%
- 7 Claude Haiku 4.5 27.6%
- 8
Qwen3-VL-4B-Instruct 13.4%
- 9 Qwen3-VL 8B 12.8%
- 10
Pixtral 12B 7.16%
- 11 Qwen2-VL-7B-Instruct 6.47%
- 12
Ovis2.5-9B 5.95%
- 13
InternVL2.5-26B 4.14%
- 14
LLaVA-OneVision 7B 3.53%
- 15
Qwen2.5-VL-7B 3.53%
- 16 Florence-VL 8B 2.93%
- 17
Qwen2.5-VL-3B 2.84%
- 18
Ovis2.5-2B 2.76%
- 19
Qwen2-VL-2B-Instruct 2.24%
- 20
SmolVLM-Instruct 2.24%
- 21
PaliGemma-3B-mix-448 1.98%
- 22 PaliGemma 3B 1.81%
- 23
LLaVA-v1.5-13B 1.81%
- 24 llava-v1.5-7b 1.03%
- 25
InternVL2-8B 0.86%
- 26
Phi-3-vision-128k-instruct 0.17%
- 27
InternVL2-1B 0.09%
Source: Official WTP-Bench leaderboard
- 79.0 GPT-4.1
- 78.2
Gemini 2.5 Pro
- 77.2
Gemini 2.5 Flash
- 65.1 Claude Sonnet 4.5
- 49.3 GPT-4o mini
- 46.9 Grok 4 Fast
- 27.6 Claude Haiku 4.5
- 13.4
Qwen3-VL-4B-Instruct
- 7.16
Pixtral 12B
- 6.47 Qwen2-VL-7B-Instruct
- 5.95
Ovis2.5-9B
- 4.14
InternVL2.5-26B
- 3.53
LLaVA-OneVision 7B
- 3.53
Qwen2.5-VL-7B
- 2.84
Qwen2.5-VL-3B
- 2.76
Ovis2.5-2B
- 2.24
Qwen2-VL-2B-Instruct
- 2.24
SmolVLM-Instruct
- 1.98
PaliGemma-3B-mix-448
- 1.81
LLaVA-v1.5-13B
- 1.03 llava-v1.5-7b
- 0.86
InternVL2-8B
- 0.17
Phi-3-vision-128k-instruct
- 0.09
InternVL2-1B
- 1 GPT-4.1 79%
- 2
Gemini 2.5 Pro Jun 2025 78.2%
- 3
Gemini 2.5 Flash Sep 2025 77.2%
- 4 Claude Sonnet 4.5 65.1%
- 5 GPT-4o mini 49.3%
- 6 Grok 4 Fast 46.9%
- 7 Claude Haiku 4.5 27.6%
- 8
Qwen3-VL-4B-Instruct 13.4%
- 9
Pixtral 12B 7.16%
- 10 Qwen2-VL-7B-Instruct 6.47%
- 11
Ovis2.5-9B 5.95%
- 12
InternVL2.5-26B 4.14%
- 13
LLaVA-OneVision 7B 3.53%
- 14
Qwen2.5-VL-7B 3.53%
- 15
Qwen2.5-VL-3B 2.84%
- 16
Ovis2.5-2B 2.76%
- 17
Qwen2-VL-2B-Instruct 2.24%
- 18
SmolVLM-Instruct 2.24%
- 19
PaliGemma-3B-mix-448 1.98%
- 20
LLaVA-v1.5-13B 1.81%
- 21 llava-v1.5-7b 1.03%
- 22
InternVL2-8B 0.86%
- 23
Phi-3-vision-128k-instruct 0.17%
- 24
InternVL2-1B 0.09%
Source: Official WTP-Bench leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4.1 | 79% | Apr 2025 | Official leaderboard | |
| 2 | | 78.2% | Jun 2025 | Official leaderboard | |
| 3 | | 77.2% | Sep 2025 | Official leaderboard | |
| 4 | Claude Sonnet 4.5 | 65.1% | Sep 2025 | Official leaderboard | |
| 5 | GPT-4o mini | 49.3% | Jul 2024 | Official leaderboard | |
| 6 | Grok 4 Fast | 46.9% | Sep 2025 | Official leaderboard | |
| 7 | Claude Haiku 4.5 | 27.6% | Oct 2025 | Official leaderboard | |
| 8 | | 13.4% | Oct 2025 | Official leaderboard | |
| 9 | Qwen3-VL 8B open weights | 12.8% | Official leaderboard | ||
| 10 | | 7.16% | Sep 2024 | Official leaderboard | |
| 11 | Qwen2-VL-7B-Instruct | 6.47% | Aug 2024 | Official leaderboard | |
| 12 | | 5.95% | Aug 2025 | Official leaderboard | |
| 13 | | 4.14% | Dec 2024 | Official leaderboard | |
| 14 | | 3.53% | Aug 2024 | Official leaderboard | |
| 15 | | 3.53% | Jan 2025 | Official leaderboard | |
| 16 | Florence-VL 8B open weights | 2.93% | Official leaderboard | ||
| 17 | | 2.84% | Jan 2025 | Official leaderboard | |
| 18 | | 2.76% | Aug 2025 | Official leaderboard | |
| 19 | | 2.24% | Aug 2024 | Official leaderboard | |
| 20 | | 2.24% | Nov 2024 | Official leaderboard | |
| 21 | | 1.98% | May 2024 | Official leaderboard | |
| 22 | PaliGemma 3B open weights | 1.81% | Official leaderboard | ||
| 23 | | 1.81% | Oct 2023 | Official leaderboard | |
| 24 | llava-v1.5-7b | 1.03% | Oct 2023 | Official leaderboard | |
| 25 | | 0.86% | Jul 2024 | Official leaderboard | |
| 26 | | 0.17% | May 2024 | Official leaderboard | |
| 27 | | 0.09% | Jul 2024 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4.1 | 79% | Apr 2025 | Official leaderboard | |
| 2 | | 78.2% | Jun 2025 | Official leaderboard | |
| 3 | | 77.2% | Sep 2025 | Official leaderboard | |
| 4 | Claude Sonnet 4.5 | 65.1% | Sep 2025 | Official leaderboard | |
| 5 | GPT-4o mini | 49.3% | Jul 2024 | Official leaderboard | |
| 6 | Grok 4 Fast | 46.9% | Sep 2025 | Official leaderboard | |
| 7 | Claude Haiku 4.5 | 27.6% | Oct 2025 | Official leaderboard | |
| 8 | | 13.4% | Oct 2025 | Official leaderboard | |
| 9 | | 7.16% | Sep 2024 | Official leaderboard | |
| 10 | Qwen2-VL-7B-Instruct | 6.47% | Aug 2024 | Official leaderboard | |
| 11 | | 5.95% | Aug 2025 | Official leaderboard | |
| 12 | | 4.14% | Dec 2024 | Official leaderboard | |
| 13 | | 3.53% | Aug 2024 | Official leaderboard | |
| 14 | | 3.53% | Jan 2025 | Official leaderboard | |
| 15 | | 2.84% | Jan 2025 | Official leaderboard | |
| 16 | | 2.76% | Aug 2025 | Official leaderboard | |
| 17 | | 2.24% | Aug 2024 | Official leaderboard | |
| 18 | | 2.24% | Nov 2024 | Official leaderboard | |
| 19 | | 1.98% | May 2024 | Official leaderboard | |
| 20 | | 1.81% | Oct 2023 | Official leaderboard | |
| 21 | llava-v1.5-7b | 1.03% | Oct 2023 | Official leaderboard | |
| 22 | | 0.86% | Jul 2024 | Official leaderboard | |
| 23 | | 0.17% | May 2024 | Official leaderboard | |
| 24 | | 0.09% | Jul 2024 | Official leaderboard |
Rankings by part
We read 3 parts from the benchmark’s own leaderboard: Ultra Ball, Great Ball and Shadow Ball. Each ranks models on one part of the test. Gemini 2.5 Pro leads 2 of them, and Claude Sonnet 4.5 leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Ultra Ball
24 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 ↑1 88.1%
- 2 GPT-4.1 ↓1 84.2%
- 3
Gemini 2.5 Flash Sep 2025 83%
- 4 Claude Sonnet 4.5 79.2%
- 5 GPT-4o mini 62%
- 6 Grok 4 Fast 59%
- 7 Claude Haiku 4.5 35.8%
- 8
Qwen3-VL-4B-Instruct 18.4%
- 9
Pixtral 12B 9.74%
- 10
Ovis2.5-9B ↑1 9.31%
Great Ball
24 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 ↑1 91.4%
- 2
Gemini 2.5 Flash Sep 2025 ↑1 86.2%
- 3 GPT-4.1 ↓2 84.7%
- 4 Claude Sonnet 4.5 81.9%
- 5 GPT-4o mini 68.7%
- 6 Grok 4 Fast 63.7%
- 7 Claude Haiku 4.5 42.1%
- 8
Qwen3-VL-4B-Instruct 22.4%
- 9
Ovis2.5-9B ↑2 13.9%
- 10
Pixtral 12B ↓1 13.3%
Shadow Ball
24 models we track have a score here.
- 1 Claude Sonnet 4.5 ↑3 53.1%
- 2 GPT-4.1 ↓1 49.5%
- 3
Gemini 2.5 Flash Sep 2025 30%
- 4 Claude Haiku 4.5 ↑3 27.4%
- 5
Gemini 2.5 Pro Jun 2025 ↓3 23%
- 6 GPT-4o mini ↓1 8.53%
- 7 Grok 4 Fast ↓1 7.93%
- 8
Qwen3-VL-4B-Instruct 3.10%
- 9
Ovis2.5-9B ↑2 2.16%
- 10
LLaVA-OneVision 7B ↑3 1.81%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official WTP-Bench 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 WTP-Bench 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
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 13 months ago, in October 2025, for Claude Haiku 4.5. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the official leaderboard (27 entries).
- Pass Models scored 24 models we track, plus 3 other entries on its leaderboard.
- Warning Newest score The newest came 13 months ago, in October 2025, for Claude Haiku 4.5.
- Note Frontier models None of the top 10 has a score. The strongest tested is Claude Sonnet 4.5 (#81).
- Pass Headroom The best is 79%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on sochastic.me: 24 rows for models we track and 3 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.