MMODELYST
Models/MiniMax-M2
MDL

MiniMax-M2

MiniMax

Verified against Artificial Analysis · Jul 13, 2026
Capability
81
percentile index
Price /M
$0.3 / $1.2
in / out
Context
204.8K
tokens
Avg score
61.5
10 benchmarks
AA Intelligence
28.3
index
Speed
78 tok/s
TTFT 1.2s
Released
Oct 26, 2025
About

MiniMax-M2 is a open-weights model in the MiniMax family from MiniMax. Benchmarked on 10 evals, averaging 61.5.

Benchmark scores · 10
avg 61.5 — higher is better
τ²-bench
86.8
LiveCodeBench
82.6
MMLU-Pro
82
AIME
78.3
GPQA Diamond
77.7
IFBench
72.3
AA Long-Context Reasoning
61
SciCode
36.1
Terminal-Bench Hard
25.8
Humanity's Last Exam
12.5
Details
PublisherMiniMax
FamilyMiniMax
Parameters
License
WeightsOpen
ReleasedOct 26, 2025
Performance & price
Output speed78 tok/s
Latency (TTFT)1.2s
First answer27s
Price in / out$0.3 / $1.2 per 1M
Blended price$0.525 / 1M
Math index78.3

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers
Artificial Analysis$1.2/M