MiniMax · mit

MiniMax M2.7

MiniMax M2.7 by MiniMax appears in 1 source with Reasoning at 53.06. Best read for Low cost, Open weights, Reasoning.

CreatorMiniMax

Release date2026-03-18

Knowledge cutoffNot published

Context205K tokens

Input price$0.3/M tokens

Output price$1.2/M tokens

Modalitytext

CountryCN

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank31ranking · source_rank

Reasoning53.06reasoning · index_reasoning

Coding38.88coding · index_code

Tool calling23.1tool_calling · index_tool_calling

Finance27.76domain · index_finance

Legal28.35domain · index_legal

Code Arena1,156.45 %coding · coding_arena_score

Toolathlon46.3 %tool_calling · toolathlon_score

SWE-bench Pro56.2 %coding · swe_bench_pro_score

Context204,800 tokenscontext · context

Speed174 c/sperformance · throughput

Latency4,881.64 msperformance · latency

Input price0.3 $/Mpricing · input_price

Output price1.2 $/Mpricing · output_price

Evidence

Citations and source overlap

LLM StatsPublic full LLM leaderboard advanced explorer snapshot, including ranking, benchmark indexes, pricing, speed, context, license, and model metadata.Retrieved 2026-06-01

FAQ

How should I read this profile?

Treat this as a source-backed model dossier, not an EvalKit-run verification. The public values are replicated from linked sources and kept source-scoped.

Is MiniMax M2.7 verified by EvalKit?

No. EvalKit currently shows 0 verified rows until real run evidence exists.

Why can metrics disagree?

Different sources test different tasks, dates, prompts, and aggregation methods. EvalKit keeps those differences visible instead of merging them into a fake universal score.