inclusionAI/LLaDA2.0-mini
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| GSM8K | math | 93.63 | GSM8K | medium | | GSM8K | 93.63 | 94.62 | 89.01 | 94.24 | |
| IFEval | instruction-following | 86.9 | IFEval-strict -prompt | medium | | IFEval-strict -prompt | 86.9 | 76.16 | 62.50 | 80.78 | |
| MATH | math | 86.28 | MATH | medium | | MATH | 86.28 | 94.66 | 73.50 | 93.22 | |
| GAOKAO | knowledge | 84.94 | GAOKAO-Bench | medium | | GAOKAO-Bench | 84.94 | 87.23 | 74.46 | 84.30 | |
| HumanEval | coding | 84.76 | HumanEval | medium | | HumanEval | 84.76 | 85.98 | 80.49 | 86.59 | |
| DROP | reasoning | 84.56 | DROP | medium | | DROP | 84.56 | 78.80 | 79.49 | 81.91 | |
| C-Eval | knowledge | 81.36 | C-EVAL | medium | | C-EVAL | 81.36 | 82.10 | 66.54 | 81.38 | |
| MMLU | knowledge | 80.94 | MMLU | medium | | MMLU | 80.94 | 82.15 | 72.49 | 80.53 | |
| HellaSwag | knowledge | 79.56 | HellaSwag | medium | | HellaSwag | 79.56 | 69.02 | 74.01 | 79.01 | |
| CMMLU | knowledge | 79.17 | CMMLU | medium | | CMMLU | 79.17 | 80.84 | 67.53 | 79.50 | |
| MBPP | coding | 78.92 | MBPP | medium | | MBPP | 78.92 | 84.07 | 77.75 | 81.50 | |
| MMLU-Pro | knowledge | 65.48 | MMLU-Pro | medium | | MMLU-Pro | 65.48 | 63.72 | 49.22 | 63.22 | |
| Math Olympiad | math | 55.33 | OlympiadBench | medium | | OlympiadBench | 55.33 | 72.30 | 36.67 | 67.70 | |
| GPQA | reasoning | 46.59 | GPQA | medium | | GPQA | 46.59 | 56.80 | 31.82 | 47.98 | |
| BigCodeBench | coding | 36.05 | BigCodeBench-Full | medium | | BigCodeBench-Full | 36.05 | 35.00 | 30.44 | 32.89 | |
| LiveCodeBench | coding | 26.38 | LiveCodeBench | medium | | LiveCodeBench | 26.38 | 34.97 | 19.93 | 31.50 | |
| AIME 2025 | math | 22.08 | AIME 2025 | medium | | AIME 2025 | 22.08 | 47.66 | 10.00 | 36.67 | |
none scraped.