Open LMM Reasoning - DynaMath - Subject-analytic geometry; Avg: leaderboard
The "DynaMath - Subject-analytic geometry; Avg" 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. 100 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Doubao-1.5-Pro | 67.7 | #287 |
| 2 | GPT-4o ChatGPT | 66.6 | |
| 3 | Gemini 2.0 Flash | 66.5 | #342 |
| 4 | GPT-4.1 (2025-04-14) | 65.1 | #250 |
| 5 | Gemini 1.5 Pro (002) | 63.1 | #349 |
| 6 | GPT-4.1 Mini | 60.3 | #355 |
| 7 | QVQ-72B-Preview | 56.9 | #440 |
| 8 | InternVL3-78B | 56.3 | #352 |
| 9 | InternVL3-38B | 55.2 | #405 |
| 10 | VLAA-Thinker-Qwen2.5VL-7B | 53.9 | #555 |
| 11 | Claude 3.5 Sonnet (20241022) | 53.4 | #291 |
| 12 | Claude 3.7 Sonnet | 52.9 | #249 |
| 13 | Taichu-VLR-7B | 52.6 | #526 |
| 14 | InternVL3-14B | 52.2 | #505 |
| 15 | InternVL2.5-78B-CoT | 51.6 | #469 |
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-dynamath-subject-analytic-geometry-avg · How It Works · Data refreshed daily, snapshot 2026-10-20.