AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
LLM Stats
AI2D
AI2D is a dataset of 4,903 illustrative diagrams from grade school natural sciences (such as food webs, human physiology, and life cycles) with over 15,000 multiple choice questions and answers. The benchmark evaluates diagram understanding and visual reasoning capabilities, requiring models to interpret diagrammatic elements, relationships, and structure to answer questions about scientific concepts represented in visual form.
Evaluation context and evidence
- Source
- LLM Stats
- Publisher
- Not recorded
- Benchmark release
- Not recorded
- Collected
- 2026-08-17
- Modality
- multimodal
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 33
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| Claude 3.5 Sonnet | 0.947 | Not recorded | Not recorded | 2024-10-22 · model_announcement | LLM Stats |
| Qwen3.6 Plus | 0.944 | Not recorded | Not recorded | 2026-04-02 · model_announcement | LLM Stats |
| GPT-4o | 0.942 | Not recorded | Not recorded | 2024-08-06 · model_announcement | LLM Stats |
| Pixtral Large | 0.938 | Not recorded | Not recorded | 2024-11-18 · model_announcement | LLM Stats |
| Qwen3.5-122B-A10B | 0.933 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| Mistral Small 3.2 24B Instruct | 0.9291 | Not recorded | Not recorded | 2025-06-20 · model_announcement | LLM Stats |
| Qwen3.5-27B | 0.929 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| Qwen3.6-35B-A3B | 0.927 | Not recorded | Not recorded | 2026-04-16 · model_announcement | LLM Stats |
| Qwen3.5-35B-A3B | 0.926 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| Llama 3.2 90B Instruct | 0.923 | Not recorded | Not recorded | 2024-09-25 · model_announcement | LLM Stats |
| Llama 3.2 11B Instruct | 0.911 | Not recorded | Not recorded | 2024-09-25 · model_announcement | LLM Stats |
| Qwen3 VL 235B A22B Instruct | 0.897 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 32B Instruct | 0.895 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 235B A22B Thinking | 0.892 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 32B Thinking | 0.889 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen2.5 VL 72B Instruct | 0.884 | Not recorded | Not recorded | 2025-01-26 · model_announcement | LLM Stats |
| Grok-1.5V | 0.883 | Not recorded | Not recorded | 2024-04-12 · model_announcement | LLM Stats |
| Qwen3 VL 30B A3B Thinking | 0.869 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 8B Instruct | 0.857 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 30B A3B Instruct | 0.85 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 8B Thinking | 0.849 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 4B Thinking | 0.849 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Gemma 3 27B | 0.845 | Not recorded | Not recorded | 2025-03-12 · model_announcement | LLM Stats |
| Gemma 3 12B | 0.842 | Not recorded | Not recorded | 2025-03-12 · model_announcement | LLM Stats |
| Qwen3 VL 4B Instruct | 0.841 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen2.5-Omni-7B | 0.832 | Not recorded | Not recorded | 2025-03-27 · model_announcement | LLM Stats |
| Phi-4-multimodal-instruct | 0.823 | Not recorded | Not recorded | 2025-02-01 · model_announcement | LLM Stats |
| DeepSeek VL2 | 0.814 | Not recorded | Not recorded | 2024-12-13 · model_announcement | LLM Stats |
| DeepSeek VL2 Small | 0.8 | Not recorded | Not recorded | 2024-12-13 · model_announcement | LLM Stats |
| Phi-3.5-vision-instruct | 0.781 | Not recorded | Not recorded | 2024-08-23 · model_announcement | LLM Stats |
| North Micro Vision Instruct | 0.775 | Not recorded | Not recorded | 2026-08-12 · model_announcement | LLM Stats |
| Gemma 3 4B | 0.748 | Not recorded | Not recorded | 2025-03-12 · model_announcement | LLM Stats |
| DeepSeek VL2 Tiny | 0.716 | Not recorded | Not recorded | 2024-12-13 · model_announcement | LLM Stats |