TPSTokens Per Second

MiniMax M2.7

MiniMax🇨🇳 China
active
Compare with other models →
Context window205K tokens
Input / 1M tokens$0.3
Output / 1M tokens$1.2

Version History

2.7major

M2.7 introduces autonomous participation in its own development through 100+ self-optimization rounds, achieving 30% performance improvement on internal coding tasks and competitive benchmark scores against leading Western models.

v1.0major

Initial release of MiniMax M2.7 — next-gen LLM with multi-agent collaboration, 204K context, SWE-Pro 56.2%, Terminal Bench 2 57.0%

Benchmark Scores

Full leaderboard →
1417.0 elo
Arena Elo
87.4%
GPQA
57.0 tokens_per_sec
Speed (tok/s)

Coverage