priorsBuilder

MiniMax · released 2026-02-12

MiniMax M2.5

Measured on 40 benchmarks.

General frontier

Not ranked in this mix — too little measured data for its benchmarks.

Your mix’s benchmarks

3 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #205default of 58720.5%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #307default of 526-38.9

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #178low of 1969.0%
  2. #180high of 1968.0%

Leader: Opus 4.8 · 95.0%

All 40 benchmarks

show 37 more

agentic

Terminal-Bench 2.0

40 results
  1. #22high of 4042.7%

Leader: GPT-5.5 · 84.7%

agentic

Vending-Bench 2

67 results
  1. #66high of 67$-23.16

Leader: GPT-6 Astra · $15,515

agentic

τ²-Bench Telecom

393 results
  1. #24default of 39395.3%

Leader: GLM 5.2 · 99.1%

coding

Arena WebDev

122 results
  1. #89high of 1221387

Leader: Opus 5.5 · 1813

coding

LiveCodeBench (Vals)

127 results
  1. #73high of 12779.2%

Leader: Fable 5.1 · 90.5%

coding

SWE Atlas-QnA

22 results
  1. #21high of 2210.3%

Leader: Opus 5 · 63.2%

coding

SWE-bench Verified (Vals)

85 results
  1. #46high of 8574.2%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #29high of 6341.6%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench Hard-AA

387 results
  1. #84default of 38734.8%

Leader: GPT-5.6 Sol · 65.9%

coding

Vibe Code Bench v1.1

105 results
  1. #81high of 10514.9%

Leader: Sonnet 5.5 · 92.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #192default of 61022.8

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #129high of 2201391

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #127high of 2201396

Leader: Gemini 4 · 1553

creative

MineBench

72 results
  1. #60high of 721115

Leader: GPT-6 Astra Pro · 2281

economics

CorpFin (Vals)

117 results
  1. #74high of 11759.6%

Leader: Opus 5 · 73.2%

economics

TaxEval (Vals)

125 results
  1. #92high of 12568.2%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #52default of 39971.6%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #211default of 52626.2%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #372default of 52611.9%

Leader: MiniCPM5-1B (Non-reasoning) · 99.1%

knowledge

CaseLaw (Vals)

53 results
  1. #40high of 5353.5%

Leader: Grok 4.3 · 79.3%

knowledge

Global-MMLU-Lite

118 results
  1. #43default of 11884.2%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #133default of 53984.8%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #62high of 12282.1%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedQA (Vals)

80 results
  1. #28high of 8092.5%

Leader: o1 · 96.5%

knowledge

MMLU Pro (Vals)

122 results
  1. #84high of 12280.1%

Leader: Fable 5.1 · 92.4%

long-context

AA-LCR v1.1

523 results
  1. #178default of 52373.3%

Leader: Kimi K3 · 88.7%

math

AIME (Vals)

82 results
  1. #29high of 8288.8%

Leader: Gemini 3.1 Pro · 98.1%

reasoning

ARC-AGI-1

215 results
  1. #134high of 21563.7%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #156high of 2164.9%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #217default of 5291.1%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #85high of 13580.0%

Leader: Fable 5 · 88.6%

reliability

Tool-call error rate

171 results
  1. #109high of 1712.2%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #168high of 18196.3%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #106default of 3511.5s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #231default of 35169.3

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #81high of 1771.2s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #110high of 17653.0

Leader: Muse Spark 1.1 · 204.3