priorsBuilder

xAI · released 2025-07-09

Grok 4

Measured on 44 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. #174default of 58726.7%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #117default of 5262.1

Leader: Opus 5.5 · 46.4

reasoning

SimpleBench

97 results
  1. #37default of 9760.5%

Leader: Opus 5.5 · 88.4%

All 44 benchmarks

show 41 more

agentic

Butter-Bench

5 results
  1. #4default of 523.0%

Leader: Gemini 2.5 Pro · 40.0%

agentic

Terminal-Bench 2.0

40 results
  1. #32default of 4027.2%

Leader: GPT-5.5 · 84.7%

agentic

τ²-Bench Telecom

393 results
  1. #141default of 39374.9%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #22default of 28281.9%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #50default of 12783.2%

Leader: Fable 5.1 · 90.5%

coding

SWE-bench Verified (Vals)

85 results
  1. #76default of 8557.8%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #48default of 6328.1%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench Hard-AA

387 results
  1. #67default of 38737.9%

Leader: GPT-5.6 Sol · 65.9%

composite

AA Intelligence Index v4.3.2

610 results
  1. #195default of 61022.5

Leader: Opus 5.5 · 57.6

economics

CorpFin (Vals)

117 results
  1. #24default of 11766.0%

Leader: Opus 5 · 73.2%

economics

MortgageTax (Vals)

84 results
  1. #77default of 8444.5%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #104default of 12565.1%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #154default of 39953.7%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #119default of 52640.5%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #179default of 52635.5%

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

knowledge

Arena Search

28 results
  1. #25default of 281142

Leader: GPT-5.6 Sol · 1257

knowledge

CaseLaw (Vals)

53 results
  1. #9default of 5365.8%

Leader: Grok 4.3 · 79.3%

knowledge

Global-MMLU-Lite

118 results
  1. #17default of 11889.5%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #95default of 53987.7%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #35default of 12288.1%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedCode

94 results
  1. #65default of 9438.1%

Leader: Opus 5 · 63.6%

knowledge

MedQA (Vals)

80 results
  1. #29default of 8092.5%

Leader: o1 · 96.5%

knowledge

MedScribe

96 results
  1. #59default of 9678.2%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #57default of 12285.3%

Leader: Fable 5.1 · 92.4%

knowledge

MMLU-Pro

285 results
  1. #15default of 28586.6%

Leader: Gemini 3 Pro · 89.8%

knowledge

MMMU Pro (Vals)

81 results
  1. #52default of 8176.3%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #155default of 26568.8%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #230default of 52368.0%

Leader: Kimi K3 · 88.7%

math

AIME (Vals)

82 results
  1. #27default of 8290.6%

Leader: Gemini 3.1 Pro · 98.1%

math

AIME 2025

228 results
  1. #16default of 22892.7%

Leader: GPT-5.2 · 99.0%

math

MATH 500 (Vals)

48 results
  1. #2default of 4896.2%

Leader: Gemini 3 Pro · 96.4%

math

MATH-500

162 results
  1. #6default of 16299.0%

Leader: GPT-5 · 99.4%

math

MGSM (Vals)

62 results
  1. #27default of 6290.9%

Leader: Opus 4.5 · 95.2%

reasoning

ARC-AGI-1

215 results
  1. #129default of 21566.7%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #130default of 21616.0%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #196default of 5292.0%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #56default of 13583.2%

Leader: Fable 5 · 88.6%

reasoning

SAGE

80 results
  1. #78default of 8025.1%

Leader: Opus 4.7 · 56.1%

reasoning

SimpleQA Verified

47 results
  1. #16default of 4751.9%

Leader: Gemini 3.1 Pro · 77.5%

speed

Latency (Time to First Token)

351 results
  1. #261default of 35113s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #222default of 35173.7

Leader: Celeris-1 · 1522.5