inclusionAI/LLaDA2.0-flash
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| MATH | math | 96.7 | MATH | medium | | MATH | 96.70 | 96.1 | 73.50 | 95.44 | |
| GSM8K | math | 96.36 | GSM8K | medium | | GSM8K | 96.36 | 95.45 | 89.01 | 96.06 | |
| GAOKAO | knowledge | 94.53 | GAOKAO-Bench | medium | | GAOKAO-Bench | 94.53 | 93.24 | 86.12 | 93.90 | |
| HumanEval | coding | 93.29 | HumanEval | medium | | HumanEval | 93.29 | 85.98 | 80.49 | 94.51 | |
| C-Eval | knowledge | 88.17 | C-EVAL | medium | | C-EVAL | 88.17 | 88.03 | 66.54 | 86.75 | |
| DROP | reasoning | 87.57 | DROP | medium | | DROP | 87.57 | 88.32 | 79.49 | 87.90 | |
| MMLU | knowledge | 87.13 | MMLU | medium | | MMLU | 87.13 | 87.98 | 83.15 | 87.69 | |
| MBPP | coding | 86.65 | MBPP | medium | | MBPP | 86.65 | 85.01 | 77.75 | 88.29 | |
| CMMLU | knowledge | 86.36 | CMMLU | medium | | CMMLU | 86.36 | 86.59 | 67.53 | 85.13 | |
| HellaSwag | knowledge | 86.31 | HellaSwag | medium | | HellaSwag | 86.31 | 81.59 | 86.00 | 84.97 | |
| IFEval | instruction-following | 84.29 | IFEval-strict -prompt | medium | | IFEval-strict -prompt | 84.29 | 81.52 | 62.50 | 81.70 | |
| Math Olympiad | math | 77.59 | OlympiadBench | medium | | OlympiadBench | 77.59 | 76.19 | 47.78 | 74.07 | |
| MMLU-Pro | knowledge | 74.23 | MMLU-Pro | medium | | MMLU-Pro | 74.23 | 76.84 | 49.22 | 73.36 | |
| AIME 2025 | math | 61.88 | AIME 2025 | medium | | AIME 2025 | 61.88 | 55.89 | 23.33 | 60.00 | |
| GPQA | reasoning | 57.34 | GPQA | medium | | GPQA | 57.34 | 67.12 | 46.59 | 61.98 | |
| LiveCodeBench | coding | 41.63 | LiveCodeBench | medium | | LiveCodeBench | 41.63 | 44.11 | 28.58 | 42.29 | |
| BigCodeBench | coding | 41.49 | Bigcodebench-Full | medium | | Bigcodebench-Full | 41.49 | 40.70 | 30.44 | 41.58 | |
none scraped.