Xiaomi, released Sep 22, 2026

MiMo-V2.6-Proprice, context, benchmarks and release details

Provisional: not enough results to rank yet Open weights 88% confidence, 2 of 3 expected sources in

57.4

SI Score

#74 of 142 ranked models

Input, per 1M tokens: $0.43
Output, per 1M tokens: $0.87
Context window: 1M
Max output: 131K
Released: Sep 22, 2026

How the score breaks down

Coding 62.4

Math —

Preference 81.1

Reasoning —

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

72 MiniMax-M2.5 57.8
73 Grok 4.20 (Reasoning) 57.7
74 MiMo-V2.6-Pro 57.4
75 GPT-5.4 nano 57.4
76 GPT-5.4 mini 56.9

Full leaderboard

Benchmark results

3 benchmarks, 3 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.

Terminal-Bench 2.1coding 89.9% 89.9

Terminal-Bench 4.0coding 34.9% 34.9

LMArena Textpreference 1491.7 elo 81.1

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, image, audio, video
First seen by SuperIndex: Oct 8, 2026
Coverage: 70% of expected source weight

Reported (2)

Official model cards via models.devOct 8, 2026
LMArena / ArenaOct 8, 2026

Awaiting (1)

LiveBench30% of weight

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