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 betterThe research behind this model
all papers mentioning it →The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence▲ 39 on HF · May 26, 2026Orchard: An Open-Source Agentic Modeling FrameworkMay 14, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
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 →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$1.2/M