DSAEval: leaderboard
Metric: Total score (0-10; mean of two LLM judges). Source: ama-cmfai.github.io. Saturation forecast: Around December 2026. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 8.16 |
| 2 | MiMo-V2-Pro | 7.91 |
| 3 | GPT-5.2 | 7.71 |
| 4 | MiniMax-M2.7 | 7.7 |
| 5 | MiMo-V2-Flash | 7.64 |
| 6 | MiniMax-M2 | 7.64 |
| 7 | Gemini 3 Pro | 7.31 |
| 8 | Grok 4.1 Fast | 7.25 |
| 9 | GPT-5 Nano | 7.07 |
| 10 | DeepSeek V3.2 | 7.03 |
| 11 | GLM-4.6V | 6.87 |
| 12 | Qwen 3 VL 30B A3B (Thinking) | 5.32 |
| 13 | Ministral 3 14B | 5.18 |
Interactive version: theaggregate.ai/benchmark?slug=dsaeval · How It Works · Data refreshed daily, snapshot 2026-09-25.