Open LMM Reasoning - LogicVista - inductive: leaderboard
The "LogicVista - inductive" subtask of Open LMM Reasoning. A task from the Open LMM Reasoning leaderboard, which evaluates large multimodal models on multi-step visual, mathematical and logical reasoning problems.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 83 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4.1 Mini | 51.4 | #355 |
| 2 | VLAA-Thinker-Qwen2.5VL-7B | 43 | #555 |
| 3 | GPT-4.1 (2025-04-14) | 41.1 | #250 |
| 4 | GPT-4o ChatGPT | 40.2 | |
| 5 | Claude 3.7 Sonnet | 39.3 | #249 |
| 6 | Doubao-1.5-Pro | 39.3 | #287 |
| 7 | Claude 3.5 Sonnet (20241022) | 37.4 | #291 |
| 8 | InternVL3-78B | 37.4 | #352 |
| 9 | Qwen 2 VL 72B | 33.6 | #460 |
| 10 | Qwen 2.5 VL 7B | 33.6 | #643 |
| 11 | Moonshot v1 8K | 32.7 | #617 |
| 12 | Taichu-VLR-3B | 32.7 | #744 |
| 13 | Grok 2 (1212) | 31.8 | #496 |
| 14 | QVQ-72B-Preview | 31.8 | #440 |
| 15 | Taichu-VLR-7B | 31.8 | #526 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-logicvista-inductive · How It Works · Data refreshed daily, snapshot 2026-10-20.