ModelBeat
Models/MiniMax-M2.5
All models
M

MiniMax: MiniMax-M2.5

Watch this modelCompareFind source
minimax/minimax-m2.5

MiniMax-M2.5 is MiniMax’s open-weights AI model, released Feb 12, 2026. It scores 147 on the Epoch Capabilities Index, costs $0.27/M input and $0.95/M output tokens, and handles a 200K-token context window.

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity.

Context
200K
Input
$0.27 / 1M
Output
$0.95 / 1M
Released
Feb 12, 2026
Modalities
text→text

Benchmarks

Scores on standardized evaluations. Higher is better — and rank shows where MiniMax-M2.5 lands among all models tracked on Model Beat.

25.0
Intelligence Index
Epoch AI
25th percentile of tracked models
26.0
Coding Index
Epoch AI
26th percentile of tracked models
34.0
Agentic Index
Epoch AI
34th percentile of tracked models

Reasoning

4 evals
ARC-AGI63.7%

Abstract visual reasoning

ARC-AGI-24.9%

Harder abstract reasoning

GPQA Diamond84.8%

Graduate-level scientific reasoning

Humanity's Last Exam20.5%

Frontier of human expert knowledge

Coding

2 evals
SciCode42.6%

Scientific research coding

WebDev Arena1384

Human-rated web development

Agentic & Tools

3 evals
APEX6.2%

Multi-step agentic tasks

Terminal-Bench42.7%

Command-line agentic tasks

τ²-bench95.3%

Tool-agent-user reliability

Changelog

19
  • MiniMax-M2.5: context window changed from 204,800 to 200,000 tokenscontext · Nov 11, 2026
  • MiniMax-M2.5: cheapest credible provider via Venice now $0.27 per 1M input tokens (was $0.295, -8%)cheapest provider · Oct 23, 2026
  • MiniMax-M2.5: cheapest credible provider via Venice now $0.95 per 1M output tokens (was $1.2, -21%)cheapest provider · Oct 23, 2026
  • MiniMax-M2.5: cheapest credible provider via AtlasCloud now $1.2 per 1M output tokens (was $0.95, +26%)cheapest provider · Oct 22, 2026
  • MiniMax-M2.5: cheapest credible provider via AtlasCloud now $0.295 per 1M input tokens (was $0.27, +9%)cheapest provider · Oct 22, 2026
  • MiniMax-M2.5: cheapest credible provider via Venice now $0.95 per 1M output tokens (was $1.2, -21%)cheapest provider · Oct 15, 2026
  • MiniMax-M2.5: cheapest credible provider via Venice now $0.27 per 1M input tokens (was $0.295, -8%)cheapest provider · Oct 15, 2026
  • MiniMax-M2.5: cheapest credible provider via AtlasCloud now $0.295 per 1M input tokens (was $0.27, +9%)cheapest provider · Oct 5, 2026
  • MiniMax-M2.5: cheapest credible provider via AtlasCloud now $1.2 per 1M output tokens (was $0.95, +26%)cheapest provider · Oct 5, 2026
  • MiniMax-M2.5: cheapest credible provider via Venice now $0.95 per 1M output tokens (was $1.2, -21%)cheapest provider · Oct 1, 2026
  • MiniMax-M2.5: cheapest credible provider via Venice now $0.27 per 1M input tokens (was $0.295, -8%)cheapest provider · Oct 1, 2026
  • MiniMax-M2.5: cheapest credible provider via AtlasCloud now $1.2 per 1M output tokens (was $0.95, +26%)cheapest provider · Sep 24, 2026
  • MiniMax-M2.5: cheapest credible provider via AtlasCloud now $0.295 per 1M input tokens (was $0.27, +9%)cheapest provider · Sep 24, 2026
  • MiniMax-M2.5: cheapest credible provider via Venice now $0.95 per 1M output tokens (was $0.9, +6%)cheapest provider · Aug 21, 2026
  • MiniMax-M2.5: cheapest credible provider via Venice now $0.27 per 1M input tokens (was $0.22, +23%)cheapest provider · Aug 21, 2026
  • MiniMax-M2.5: vendor list price cut from $0.6 to $0.3 per 1M input tokens (-50%)list price · Aug 15, 2026
  • MiniMax-M2.5: vendor list price cut from $2.4 to $1.2 per 1M output tokens (-50%)list price · Aug 15, 2026
  • MiniMax-M2.5: cheapest credible provider via Inceptron now $0.22 per 1M input tokens (was $0.15, +47%)cheapest provider · Aug 8, 2026
  • MiniMax-M2.5: Humanity's Last Exam improved from 19.1% to 20.5% (+7%)benchmark · Aug 6, 2026

Compare MiniMax-M2.5 with

MiniMax-M2.5 vs GPT-6 AstraMiniMax-M2.5 vs Claude Opus 5.5MiniMax-M2.5 vs Gemini 3.8 FlashMiniMax-M2.5 vs Kimi K3MiniMax-M2.5 vs Grok 4.6

Frequently asked questions

What is MiniMax-M2.5?

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity.

Who created MiniMax-M2.5?

MiniMax-M2.5 is an AI model developed by MiniMax, part of the MiniMax family, released Feb 12, 2026.

How much does MiniMax-M2.5 cost?

MiniMax-M2.5 is served from $0.27 per million input tokens and $0.95 per million output tokens (cheapest credible provider on OpenRouter: Venice).

What is MiniMax-M2.5's context window?

MiniMax-M2.5 supports a context window of up to 200K tokens.

How does MiniMax-M2.5 perform on benchmarks?

On standardized evaluations tracked by Epoch AI, MiniMax-M2.5 scores 95.3% on τ²-bench, 42.6% on SciCode, 84.8% on GPQA Diamond.

Is MiniMax-M2.5 open source?

MiniMax-M2.5 is released with open weights (Open weights (unrestricted)), so the model can be downloaded and self-hosted.

Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Nov 12, 2026.