Open LMM Reasoning - LogicVista - spatial: leaderboard
The "LogicVista - spatial" 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 | 34.6 | #355 |
| 2 | InternVL3-38B | 34.6 | #405 |
| 3 | Doubao-1.5-Pro | 34.6 | #287 |
| 4 | Gemini 2.0 Flash | 33.3 | #342 |
| 5 | VLM-R1-3B-Math-0305 | 33.3 | #743 |
| 6 | GPT-4.1 (2025-04-14) | 30.8 | #250 |
| 7 | Claude 3.7 Sonnet | 30.8 | #249 |
| 8 | Qwen 2 VL 72B | 30.8 | #460 |
| 9 | Moonshot v1 8K | 30.8 | #617 |
| 10 | QVQ-72B-Preview | 30.8 | #440 |
| 11 | Grok 2 (1212) | 29.5 | #496 |
| 12 | GPT-4o ChatGPT | 29.5 | |
| 13 | Gemini 1.5 Pro (002) | 28.2 | #349 |
| 14 | Taichu-VLR-7B | 28.2 | #526 |
| 15 | Taichu-VLR-3B | 28.2 | #744 |
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-spatial · How It Works · Data refreshed daily, snapshot 2026-10-20.