Individual benchmark scores plotted by date.
| Organisation | Model | Reported | Top Score | Info | Self Reported | Source |
|---|---|---|---|---|---|---|
| Kimi K2 (2025-07-11) | 11 Jul 2025 | 80.30% | Pass@1 | Yes | Source | |
| Qwen 2 Math 72B | - | 79% | inferred high-confidence family alias from qwen2-72b-instruct (score=0.4667; benches=17) | Yes | Source | |
| Qwen 2 Math RM 72B | - | 79% | inferred family alias from qwen2-72b-instruct (score=0.3917; benches=17) | Yes | Source | |
| Qwen 3 235B A22B | - | 77.60% | - | Yes | Source | |
| Qwen 2 Audio 7B | - | 70.30% | inferred modality/version alias from qwen2-7b-instruct | Yes | Source | |
| Qwen 2 Math 7B | - | 70.30% | inferred high-confidence family alias from qwen2-7b-instruct (score=0.4706; benches=14) | Yes | Source |
