# AI2D_TEST leaderboard

Multimodal & Grounded benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/multimodal-grounded-ai2d-test

AI2D test split. Every model the catalog carries a published AI2D_TEST value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Multimodal & Grounded |
| Measure | Diagram-grounded QA |
| Tasks | Diagram understanding |
| Difficulty | Structured visual reasoning |
| Published by | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |

A diagram understanding benchmark focused on scientific and educational visual question answering.

## AI2D_TEST ranking

8 models with a published AI2D_TEST value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Diagram-grounded QA | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Gemini 3 Pro](https://modelscale.dev/models/gemini-3-pro) | Google | 94.1 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Qwen3.5 397B](https://modelscale.dev/models/qwen3-5-397b) | Alibaba | 93.9 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Qwen3.6-35B-A3B](https://modelscale.dev/models/qwen3-6-35b-a3b) | Alibaba | 92.7 | Observed 2026-11-21 · source benchlm:models |
| 4 | [GPT-5.2](https://modelscale.dev/models/gpt-5-2) | OpenAI | 92.2 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Kimi K2.5](https://modelscale.dev/models/kimi-k2-5) | Moonshot AI | 90.8 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Nemotron 3 Nano Omni 30B A3B](https://modelscale.dev/models/nemotron-3-nano-omni-30b-a3b) | NVIDIA | 88.5 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Claude Opus 4.5](https://modelscale.dev/models/claude-opus-4-5) | Anthropic | 87.7 | Observed 2026-11-21 · source benchlm:models |
| 8 | [ZAYA1-VL-8B](https://modelscale.dev/models/zaya1-vl-8b) | Zyphra | 87.5 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
