Arena.ai
@arena
MiniMax M2.7 is ranked #8 in Code Arena. It’s also the most cost-efficient of the top 10 at $0.30 / $1.20 per MToken. Congrats to the team at @MiniMax_AI 👏 https://t.co/jKUvcDSUMC
27retweets
View on XMiniMax M2.7 Enters Code Arena Top 10 as Most Cost-Efficient Model
· Updated
MiniMax M2.7, an agentic language model from MiniMax, holds a preliminary rank of #8 on Code Arena's Agentic WebDev leaderboard with a score of 1452. It's priced at $0.30 input / $1.20 output per million tokens with a 204.8K context window. By comparison, the top five models — all Anthropic Claude variants — range from $3 to $25 per million tokens.
That cost gap is significant. MiniMax M2.7 sits inside the top 10 at over 16x lower input cost than the Claude Opus models above it, while posting a score close to models ranked 5th through 7th. On SWE-Pro, M2.7 scores 56.22%, matching GPT-5.3-Codex, and on VIBE-Pro it scores 55.6% — near Opus 4.6 levels on repo-level code generation.
Evaluate M2.7 against your current model spend on agentic coding tasks — the leaderboard includes price and context window data across all ranked models.
