Scores updated · 18 tests both models report · How we compare
Every test, side by side
All 18 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results18 tests
- HumanEvalHunyuan Large by 28.143.371.4+28.1
- MATHHunyuan Large by 26.443.469.8+26.4
- NaturalQuestionsHunyuan Large by 14.238.652.8+14.2
- GSM8KHunyuan Large by 13.679.292.8+13.6
- MMLUHunyuan Large by 12.875.688.4+12.8
- CMathHunyuan Large by 12.678.791.3+12.6
- C-EvalHunyuan Large by 10.581.491.9+10.5
- TriviaQAHunyuan Large by 9.379.989.2+9.3
- DROPHunyuan Large by 8.880.188.9+8.8
- MMLU-ProHunyuan Large by 8.851.460.2+8.8
- MBPPHunyuan Large by 7.66572.6+7.6
- BBHHunyuan Large by 7.578.886.3+7.5
- CMMLUHunyuan Large by 6.28490.2+6.2
- C3Hunyuan Large by 4.977.482.3+4.9
- PIQAHunyuan Large by 4.483.988.3+4.4
- ARC-ChallengeHunyuan Large by 2.892.295+2.8
- WinoGrandeHunyuan Large by 2.486.388.7+2.4
- HellaSwagtie87.186.8tie
Questions people ask
How do you compare the two?
We use the 18 benchmark tests both models have published scores on. None of them is in the eight capability areas we count, so this page lists them without a verdict. Each score is the one shown on the model's own page.