Expired50% confidenceFactExact time
In the complex codebase feature expansion task, when Composer 2.5 had already completed the task, MiniMax M3 was still analyzing the codebase, but the final output contained more comments and more comprehensive test coverage.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
MiniMax M3 Coding Benchmark: 1/765th the Price of Opus, but Better Code Quality?
bilibili认真的笨笨6/22/2026
Related Claims
UnverifiedMiniMax M3 received an average score of 58.3 across 7 high-difficulty coding tasks in a systematic evaluation74% similarUnverifiedMiniMax M2.7采用230亿参数的稀疏MoE（混合专家）架构，每个token仅激活100亿参数69% similarUnverifiedIn MiniMax's MMClaw evaluation, M2.7 approaches the level of Sonnet 4.6 in open-ended tool-calling scenarios67% similarUnverifiedMiniMax M2.1's performance on the SWE-Bench benchmark is on par with or even surpasses Claude Sonnet 4.5.67% similarUnverifiedThe model used in the demonstration is MiniMax M3, not the highest-performing model on the market; the selection criteria were sufficiency and cost reliability.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/41665API
curl https://kongchang.com/api/v1/knowledge/claims/41665MCP
get_claim(id=41665)