MMLU#5 of 28
acc
View run →81.6%±0.3%
Benchmark results loaded.
MiniMax/MiniMax-M2-AWQ
- Weights
- 120.9 GB · safetensors
- Source
- huggingface page
- Commit
- 3f6771a
Evaluated across 12 benchmarks. Ranks in the top 3 on 0 of 12. Strongest showing on MMLU (81.6% acc, #5 of 28). Weakest on BBH (0.1% exact_match, #24 of 28).
Benchmark results
| Benchmark | Metric | Score | Rank | Actions |
|---|---|---|---|---|
| MMLU | acc | 81.6%±0.3% | #5 of 28 | View run → |
| MGSM | exact_match | 63.3%±0.8% | #14 of 28 | View run → |
| MMLU-Pro | exact_match | 59.3%±0.4% | #16 of 28 | View run → |
| IFEval | prompt_level_strict_acc | 40.3%±2.1% | #26 of 28 | View run → |
| GSM8K | exact_match | 28.8%±1.2% | #23 of 28 | View run → |
| GPQA Diamond | acc | 25.8%±3.1% | #25 of 28 | View run → |
| GPQA Extended | acc | 24.9%±1.9% | #23 of 28 | View run → |
| GPQA Main | acc | 21.4%±1.9% | #28 of 28 | View run → |
| LongBench | aggregate | 19.0%±0.3% | #8 of 17 | View run → |
| MBPP | pass@1 | 1.2%±0.5% | #21 of 28 | View run → |
| EQ-Bench | eqbench | 0.5±0.5 | #28 of 28 | View run → |
| BBH | exact_match | 0.1%±0.0% | #24 of 28 | View run → |
- MGSM#14 of 28exact_matchView run →63.3%±0.8%
- MMLU-Pro#16 of 28exact_matchView run →59.3%±0.4%
- IFEval#26 of 28prompt_level_strict_accView run →40.3%±2.1%
- GSM8K#23 of 28exact_matchView run →28.8%±1.2%
- GPQA Diamond#25 of 28accView run →25.8%±3.1%
- GPQA Extended#23 of 28accView run →24.9%±1.9%
- GPQA Main#28 of 28accView run →21.4%±1.9%
- LongBench#8 of 17aggregateView run →19.0%±0.3%
- MBPP#21 of 28pass@1View run →1.2%±0.5%
- EQ-Bench#28 of 28eqbenchView run →0.5±0.5
- BBH#24 of 28exact_matchView run →0.1%±0.0%
last evaluated:6 months ago
How to cite
Citation
FrozeBench. "MiniMax/MiniMax-M2-AWQ." https://frozebench.com/models/minimax-minimax-m2-awq. Retrieved 2026-06-04.
BibTeX
@misc{frozebench_MiniMax_MiniMax_M2_AWQ,
title = {MiniMax/MiniMax-M2-AWQ},
howpublished = {\url{https://frozebench.com/models/minimax-minimax-m2-awq}},
year = {2026},
note = {FrozeBench. Retrieved 2026-06-04.}
}URL
https://frozebench.com/models/minimax-minimax-m2-awq