Hunyuan-TurboS ranks first on CMMLU.
Tencent Feb 2025 Closed weights Flagship
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BIG-Bench Hard | 92.2% | #4 of 71 | Model card | |
| CMMLU | 90.8% | #1 of 17 | Model card | |
| DROP | 91.5% | #5 of 40 | Model card | |
| MMLU | 89.5% | #18 of 127 | Model card | |
| Arena-Hard-Auto | 88.6% | #12 of 39 | Model card | |
| IFEval | 88.6% | #43 of 126 | Model card | |
| C-Eval | 90.9% | #13 of 38 | Model card | |
| LMArena (Elo) | 1,383 | #149 of 333 | Official leaderboard | |
| MMLU-Pro | 79% | #81 of 151 | Model card | |
| Chinese SimpleQA | 70.8% | #7 of 13 | Model card | |
| SimpleQA | 22.8% | #35 of 59 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MATH | 89.7% | #10 of 93 | Model card | |
| GPQA Diamond | 57.5% | #213 of 284 | Model card | |
| AIME 2024 | 43.3% | #76 of 87 | Model card | |
| ZebraLogic | 46% | #23 of 23 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HumanEval | 91% | #11 of 95 | Model card | |
| AutoCodeBench | 43.8% | #18 of 34 | Official leaderboard | |
| LiveCodeBench | 32% | #61 of 73 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LiveBench | 61% | #16 of 27 | Model card |
The benchmarks the lab chose to headline, with the scores it gave.