MiniMax-M2.7
MiniMax- Arena score
- 1405
- Among open models
- #45of 148
- Among all on Arena
- #151
- Votes
- 89,429
Measured on MiniMax-M2.7, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- Coding1453#28#9825.2K
- Software & IT1446#34#11335.8K
- Expert1443#26#928.8K
- Hard prompts, English1440#31#10824.7K
- Chinese1439#46#1445.9K
- Applied math1437#31#994.7K
- English1425#40#13036.7K
- French1425#37#1273.4K
- Hard prompts1422#38#13158K
- Math1422#37#1214.5K
- Long prompts1418#31#11437.9K
- Science1416#46#15314.2K
- Multi-turn1412#37#13415.2K
- Medicine & health1410#43#1506.1K
- Business & finance1407#42#13117.2K
- Spanish1406#43#1382.9K
- Instructions1405#32#11929.9K
- Legal & government1402#47#1576.8K
- German1398#38#1301.5K
- Excluding ties1388#45#15067.6K
- Polish1386#39#1401.7K
- Non-English1383#50#16452.8K
- Russian1383#48#16411K
- Writing & literature1376#41#15621.9K
- Media & sports1360#44#15819.9K
- Creative writing1354#45#16515.4K
- Korean1314#46#1651.5K
- Japanese1252#55#1901.2K
About as strong, smaller
Compare
gemma-4-26B-A4B-itGoogle143425.8B

Qwen3.8-27BQwen143727.8B

Qwen3.5-27BQwen140927.8B

gemma-4-31B-itGoogle144331.3B
Discussion
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiounsloth/MiniMax-M2.7-GGUF35 builds
- MLX · Apple silicon: mlx-lm, LM StudioJANGQ-AI/MiniMax-M2.7-JANGTQ39 builds
- AWQ · vLLM, SGLanget0dev/MiniMax-M2.7-AWQ-4bit3 builds
- GPTQ · vLLM, SGLangMJPansa/MiniMax-M2.7-REAP-172B-A10B-AutoRound-W4A161 build
Most downloaded
- MiniMax-M2.7-GGUFunsloth · Quantization10.2K downloads
- MiniMaxAI_MiniMax-M2.7-GGUFbartowski · Quantization4.7K downloads
- MiniMax-M2.7-Abliterated-Heretic-GGUFYoussofal · Quantization3.8K downloads
- MiniMax-M2.7-NVFP4nvidia · Quantization3.4K downloads
- MiniMax-M2.7-GGUFlmstudio-community · Quantization2.7K downloads
BenchClub runs
Not runnable yet
Runs open once a MiniMax-M2.7 build is registered.
More from MiniMax
See more
MiniMax-M2.51M229B

MiniMax-M3125.6K427B

MiniMax-M2.113.9K229B

MiniMax-M2112.4K229B
Other 80–300B models
See more
DeepSeek-V4-FlashDeepSeek1.2M291B
Inkling-SmallThinking Machines1M266B
Hy3Tencent987.2K299B

NVIDIA-Nemotron-3-Super-120B-A12B-BF16NVIDIA874.7K124B