Scores updated · 15 tests both models report · How we compare
Every test, side by side
All 15 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results15 tests
- MATHHunyuan Large by 9.760.169.8+9.7
- HumanEvalHunyuan Large by 9.561.971.4+9.5
- GSM8KHunyuan Large by 8.484.492.8+8.4
- TriviaQAHunyuan Large by 5.383.989.2+5.3
- WinoGrandeHunyuan Large by 5.383.488.7+5.3
- PIQAHunyuan Large by 3.285.188.3+3.2
- MMLU-ProDeepSeek-V3.2-Exp-Base by 3.163.360.2+3.1
- MBPPDeepSeek-V3.2-Exp-Base by 375.672.6+3
- HellaSwagDeepSeek-V3.2-Exp-Base by 2.689.486.8+2.6
- BBHDeepSeek-V3.2-Exp-Base by 2.488.786.3+2.4
- DROPHunyuan Large by 2.386.688.9+2.3
- CMMLUHunyuan Large by 1.388.990.2+1.3
- C-Evaltie9191.9tie
- MMLUtie87.888.4tie
- ARC-Challengetie95.295tie
Questions people ask
How do you compare the two?
We use the 15 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.