MiniMax-M2.5
Context 205K tokens
Top 5 cheapest providers (Adjusted $/task)
The same list price can give a different adjusted $/task (caching, token efficiency) — click a price for its inputs.
Within the active global provider, residency and confidentiality filters.
| # | Provider | Platform | Raw input $/1M | Raw output $/1M | Adjusted $/task |
|---|---|---|---|---|---|
| 1 | Venice | OpenRouter | $0.270 | $0.950 | |
| 2 | Novita | OpenRouter | $0.300 | $1.20 | |
| 3 | DigitalOcean | OpenRouter | $0.300 | $1.20 | |
| 4 | TensorX | TensorX | $0.300 | $1.20 | |
| 5 | AWS Bedrock | AWS Bedrock | $0.360 | $1.44 |
Composite
2 of 7 inputs · 1 from the model family6 radar axes: DesignArena's two boards share one52.9
AA Coding —Coding Agent v1.4 —AA Intelligence 22.8AA Agentic —Epoch ECI 146.5Software ECI —DesignArena —/—
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
19 of 140 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
- Epoch ECI · attached
Agentic
Terminal-Bench Hard (AA)8034.8%
Terminal-Bench Hard (AA) pinned revision 74221fb ↗ · Published board — Tests a pinned 44-task hard subset of terminal-based work using Terminus 2.
τ²-Bench Airline (OpenRouter run)3664.1%
τ²-Bench Airline (OpenRouter run) published 2026-09-15 ↗ · Published board — Multi-turn service agents making tool calls under strict policy constraints. (OpenRouter's own reproducible run, as published on openrouter.ai/benchmarks.)
Coding
SWE Atlas Codebase QnA (Scale AI)010.3%
SWE Atlas Codebase QnA (Scale AI) published 2026-09-15 ↗ · Published board — How well a coding agent answers deep questions about a real codebase, graded against expert rubrics.
SWE Atlas Test Writing (Scale AI)018.6%
SWE Atlas Test Writing (Scale AI) published 2026-09-15 ↗ · Published board — Whether a coding agent writes production-grade tests for real repositories, graded with rubrics and LLM judges.
SWE Atlas Refactoring (Scale AI)019.5%
SWE Atlas Refactoring (Scale AI) published 2026-09-15 ↗ · Published board — Whether a coding agent restructures production code while preserving its behaviour, graded by tests and rubrics.
Efficiency
GPQA Diamond (OpenRouter run) — measured cost per task59$0.015
GPQA Diamond (OpenRouter run) — measured cost per task published 2026-09-15 ↗ · Published board — Mean USD OpenRouter actually spent per task while running GPQA Diamond for this configuration.
τ²-Bench Airline (OpenRouter run) — measured cost per task85$0.016
τ²-Bench Airline (OpenRouter run) — measured cost per task published 2026-09-15 ↗ · Published board — Mean USD OpenRouter actually spent per task while running τ²-Bench Airline for this configuration.
Instruction-following
IFBench (AA single-turn)8871.6%
IFBench (AA single-turn) published 2026-09-10 ↗ · Published board — Tests precise single-turn instructions with deterministic rule checks.
Knowledge
Humanity's Last Exam (AA text-only)7220.5%
Humanity's Last Exam (AA text-only) published 2026-09-10 ↗ · Published board — Tests expert-level knowledge on AA's text-only Humanity's Last Exam subset.
AA-Omniscience Index48-38.9
AA-Omniscience Index published 2026-09-10 ↗ · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.
UGI NatInt8938.6
UGI NatInt published 2026-09-10 ↗ · Published board — A private-question evaluation of general knowledge and reasoning across textbook, popular-culture and world-model topics.
Long-context
AA-LCR v1.17473.3%
AA-LCR v1.1 v1.1 ↗ · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.
Reasoning
AA Intelligence Index7622.8
AA Intelligence Index published 2026-09-19 ↗ · Published board — Artificial Analysis publishes this board without a version number; we keep the date each result was retained.
Science
CritPt (AA)651.1%
CritPt (AA) published 2026-09-10 ↗ · Published board — Tests research-level physics reasoning with Python, symbolic and numerical answers.
GPQA Diamond (AA)7884.8%
GPQA Diamond (AA) published 2026-09-10 ↗ · Published board — Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.
GPQA Diamond (OpenRouter run)6784.1%
GPQA Diamond (OpenRouter run) published 2026-09-15 ↗ · Published board — Graduate-level science questions that resist retrieval and reward careful reasoning. (OpenRouter's own reproducible run, as published on openrouter.ai/benchmarks.)
Tool-use
τ²-Bench Telecom (AA)9595.3%
τ²-Bench Telecom (AA) published 2026-09-10 ↗ · Published board — Tests dual-control telecom agents that coordinate tool use with a simulated user.
Uncensored
UGI Willingness21.00
UGI Willingness published 2026-09-10 ↗ · Published board — A private-question evaluation of how far a model follows challenging instructions before refusing or deviating.
UGI1818.1
UGI published 2026-09-10 ↗ · Published board — A private-question suite combining sensitive-topic knowledge with willingness to follow controversial instructions.
Writing
UGI Writing8141.7
UGI Writing published 2026-09-10 ↗ · Published board — A maintainer-owned writing evaluation considering intelligence, style, repetition and length adherence, informed by human preferences.
Unusual results
1 threshold-crossing signal flagged · 17 eligible benchmark families
How flags are calculated
Heuristic screen, not statistical significance: benchmark families are correlated and source uncertainty is unknown. Peer evidence needs ≥ 20 independently measured matched configurations from ≥ 10 distinct model families. A flag needs a directed population z-score of magnitude ≥ 1.5 and a gap of ≥ 1.5 from the leave-one-benchmark-family-out mean z in the same direction, over ≥ 5 other benchmark families.
- unusually weak UGI Willingness published 2026-09-10
Why
Observed: 1 pointsPeer mean 3.63378 · peer sd 1.73698 · n 74 · families 73Directed z -1.516 · baseline z 0.533 · gap -2.05 · profile n 161 pointsmeasuredobserved 2026-09-10huggingface.co ↗Evidence
Axis: UGI Willingness · published 2026-09-10 · Published boardExact value:1pointsObserved: 2026-09-10T22:04:13Z · publication date: not recordedObservation id:public:96a76da1ca997020970b276f
Missing coverage · 125 benchmark versions
No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.
Token offers by platform · 5 offers (Adjusted $/task)
Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.
5 offers within the active global filters; “—” means the catalog is active but no public token price is available.
OpenRouter (3)
| Novita | globalnovita/fp8 | $0.300 raw in $/1M | $1.20 raw out $/1M | |
| DigitalOcean | globaldigitalocean | $0.300 raw in $/1M | $1.20 raw out $/1M | |
| Venice | globalvenice | $0.270 raw in $/1M | $0.950 raw out $/1M |
TensorX (1)
| TensorX | euEU | $0.300 raw in $/1M | $1.20 raw out $/1M |
AWS Bedrock (1)
| AWS Bedrock | eu-central-1EU | $0.360 raw in $/1M | $1.44 raw out $/1M |