Scientific Reasoning on HLE Text-only
13.7AccuracyQwen3-Next-80B-A3B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-Next-80B-A3BParameters=80B2026.02 | 13.7 | |
| Nanbeige4.1-3BParameters=3B2026.02 | 12.6 | |
| Qwen3-30B-A3B-2507Parameters=30B2026.02 | 11.77 | |
| Nanbeige4-3B-2511Parameters=3B2026.02 | 10.98 | |
| Qwen3-32BParameters=32B2026.02 | 9.31 | |
| Qwen3-4B-2507Parameters=4B2026.02 | 6.72 |