unsloth/MiniMax-M2.1-GGUF
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| MMLU-Pro | knowledge | 88.0 | MMLU-Pro | medium | | MMLU-Pro | 88.0 | 82.0 | 88.0 | 90.0 | 90.0 | 87.0 | 86.0 | |
| AIME 2025 | math | 83.0 | AIME25 | medium | | AIME25 | 83.0 | 78.0 | 88.0 | 91.0 | 96.0 | 98.0 | 92.0 | |
| GPQA | reasoning | 83.0 | GPQA-D | medium | | GPQA-D | 83.0 | 78.0 | 83.0 | 87.0 | 91.0 | 90.0 | 84.0 | |
| SWE-bench Verified | swe | 74.0 | SWE-bench Verified | medium | | SWE-bench Verified | 74.0 | 69.4 | 77.2 | 80.9 | 78.0 | 80.0 | 73.1 | |
| SWE-bench Verified | swe | 71.3 | SWE-bench Verified (Droid) | medium | | SWE-bench Verified (Droid) | 71.3 | 68.1 | 72.3 | 75.2 | x | x | 67.0 | |
| IFBench | instruction-following | 70.0 | IFBench | medium | | IFBench | 70.0 | 72.0 | 57.0 | 58.0 | 70.0 | 75.0 | 61.0 | |
| SWE-bench Verified | swe | 67.0 | SWE-bench Verified (mini-swe-agent) | medium | | SWE-bench Verified (mini-swe-agent) | 67.0 | 61.0 | 70.6 | 74.4 | 71.8 | 74.2 | 60.0 | |
| BrowseComp | agentic | 62.0 | BrowseComp (context management) | medium | | BrowseComp (context management) | 62.0 | 56.9 | 26.1 | 57.8 | 59.2 | 70.0 | 67.6 | |
| Terminal-Bench 2.0 | agentic-coding | 47.9 | Terminal-bench 2.0 | medium | | Terminal-bench 2.0 | 47.9 | 30.0 | 50.0 | 57.8 | 54.2 | 54.0 | 46.4 | |
| BrowseComp | agentic | 47.4 | BrowseComp | medium | | BrowseComp | 47.4 | 44.0 | 19.6 | 37.0 | 37.8 | 65.8 | 51.4 | |
| SciCode | coding | 41.0 | SciCode | medium | | SciCode | 41.0 | 36.0 | 45.0 | 50.0 | 56.0 | 52.0 | 39.0 | |
| Humanity's Last Exam | knowledge | 22.2 | HLE w/o tools | medium | | HLE w/o tools | 22.2 | 12.5 | 17.3 | 28.4 | 37.2 | 31.4 | 22.2 | |
| Terminal-Bench | agentic-coding | 2.0 | medium | Terminal-bench 2.0 |
none scraped.