Help keep public data accurate
See something missing, incorrect, or out of date? Tell us about this page.
See something missing, incorrect, or out of date? Tell us about this page.
AI benchmark results and model performance
Individual benchmark scores plotted by date.
| Organisation | Models | Reported | Top score | Info | Self reported | Source |
|---|---|---|---|---|---|---|
| Beam | 05 Oct 2026 | 97.80% | Reflection-reported launch score. Source row: AIME 2026. Accessed 2026-10-05T22:51:12.456Z. Harness, reasoning effort, sampling and trial count are not specified per row. Not independently reproduced. | Yes | Source | |
| Qwen 3.6 Plus | 01 Apr 2026 | 95.30% | - | Yes | Source | |
| GLM 5.1 | 07 Apr 2026 | 95.30% | - | Yes | Source | |
| Muse Glimmer 30B | 10 Aug 2026 | 94.70% | High reasoning | Yes | Source | |
| Seed 2.0 Pro | 14 Feb 2026 | 94.20% | - | Yes | Source | |
| Qwen 3.5 397B A17B | 16 Feb 2026 | 91.30% | - | Yes | Source | |
| Gemma 4 31B | 02 Apr 2026 | 89.20% | No tools | Yes | Source | |
| Seed 2.0 Lite | 14 Feb 2026 | 88.30% | - | Yes | Source | |
| Gemma 4 26B A4B | 02 Apr 2026 | 88.30% | No tools | Yes | Source | |
| Seed 2.0 Mini | 14 Feb 2026 | 86.70% | Seed2 official benchmark table | AIME 2026 | Yes | Source | |
| Gemma 4 12B | 03 Jun 2026 | 77.50% | No tools | Yes | Source | |
| DiffusionGemma 26B A4B IT | 10 Jun 2026 | 69.10% | No tools | Yes | Source |
