MiniMax, released Feb 12, 2026

MiniMax-M2.5price, context, benchmarks and release details

Provisional: not enough results to rank yet Open weights 100% confidence, 4 of 5 expected sources in

57.8

SI Score

#72 of 142 ranked models

Input, per 1M tokens: $0.30
Output, per 1M tokens: $1.20
Context window: 205K
Max output: 131K
Released: Feb 12, 2026

How the score breaks down

Coding 75.8

Math —

Preference 68.9

Reasoning 33.3

Weights: reasoning 30%, math 15%, coding 40%, preference 15%. Results use fixed 0–100 scales before averaging, and thin evidence is pulled toward 50. Method si-v3-retained-evidence-2, computed Oct 9, 2026, 05:13 UTC.

Around it on the leaderboard

70 MiniMax-M2.7 57.9
71 Fugu Ultra 57.9
72 MiniMax-M2.5 57.8
73 Grok 4.20 (Reasoning) 57.7
74 MiMo-V2.6-Pro 57.4

Full leaderboard

Benchmark results

6 benchmarks, 7 results

Each row shows the best published result. Where a model was tested at several settings, such as reasoning effort, open the row to see each one. Hover or tap a value for its source.

ARC-AGI-1 (public eval)reasoning 59.1% 59.1

ARC-AGI-1 (semi-private)reasoning 63.7% 63.7

ARC-AGI-2 (public eval)reasoning 5.4% 5.4

ARC-AGI-2 (semi-private)reasoning 4.9% 4.9

SWE-bench Verifiedcoding 75.8% 75.8 2 settings

About SWE-bench Verified

LMArena Textpreference 1359.4 elo 68.9

Normalization uses a fixed 0–100 scale for each unit, independent of other models. Compare evaluation conditions before reading a small gap as decisive. “Lab-reported” marks the provider's own published figure.

Details and sources

Open weights: Yes
License: not yet reported
Input modalities: text
First seen by SuperIndex: Oct 8, 2026
Coverage: 81% of expected source weight

Reported (4)

ARC PrizeOct 8, 2026
Official model cards via models.devOct 8, 2026
LMArena / ArenaOct 8, 2026
SWE-bench VerifiedOct 8, 2026

Awaiting (1)

LiveBench19% of weight

Confidence rises as pending sources publish. Some sources never cover some models, so confidence reaches 100% at 80% of expected weight.