priorsBuilder

xAI · released 2025-10-21

Grok 4 Fast

Measured on 42 benchmarks.

General frontier

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

Your mix’s benchmarks

2 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #216default of 58719.1%
  2. #479none of 5874.5%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #273default of 526-29.9
  2. #406none of 526-54.4

Leader: Opus 5.5 · 46.4

All 42 benchmarks

show 40 more

agentic

τ²-Bench Telecom

393 results
  1. #170default of 39365.8%
  2. #177none of 39363.7%

Leader: GLM 5.2 · 99.1%

coding

Arena WebDev

122 results
  1. #121none of 1221159

Leader: Opus 5.5 · 1813

coding

LiveCodeBench

282 results
  1. #19default of 28283.2%
  2. #152none of 28240.1%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #76none of 12779.0%

Leader: Fable 5.1 · 90.5%

coding

SWE-bench Verified (Vals)

85 results
  1. #81none of 8545.4%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #45none of 6329.2%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench Hard-AA

387 results
  1. #168default of 38718.9%
  2. #209none of 38712.1%

Leader: GPT-5.6 Sol · 65.9%

coding

Vibe Code Bench v1.1

105 results
  1. #104none of 1050.0%

Leader: Sonnet 5.5 · 92.4%

coding

WeirdML v2

127 results
  1. #79none of 12742.9%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #251default of 61017.9
  2. #354none of 61011.1

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #103none of 2201419

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #102none of 2201422

Leader: Gemini 4 · 1553

economics

CorpFin (Vals)

117 results
  1. #16none of 11766.9%

Leader: Opus 5 · 73.2%

economics

MortgageTax (Vals)

84 results
  1. #80none of 8442.1%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #13none of 12575.7%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #170default of 39950.5%
  2. #278none of 39937.7%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #257default of 52622.8%
  2. #342none of 52617.7%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #205default of 52631.7%
  2. #364none of 52612.4%

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

knowledge

Arena Search

28 results
  1. #19none of 281171

Leader: GPT-5.6 Sol · 1257

knowledge

CaseLaw (Vals)

53 results
  1. #10none of 5365.7%

Leader: Grok 4.3 · 79.3%

knowledge

Global-MMLU-Lite

118 results
  1. #35default of 11885.9%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #135default of 53984.7%
  2. #356none of 53960.6%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #49none of 12285.4%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedCode

94 results
  1. #68none of 9437.4%

Leader: Opus 5 · 63.6%

knowledge

MedQA (Vals)

80 results
  1. #33none of 8092.1%

Leader: o1 · 96.5%

knowledge

MedScribe

96 results
  1. #48none of 9681.6%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #88none of 12279.7%

Leader: Fable 5.1 · 92.4%

knowledge

MMLU-Pro

285 results
  1. #29default of 28585.0%
  2. #162none of 28573.0%

Leader: Gemini 3 Pro · 89.8%

knowledge

MMMU Pro (Vals)

81 results
  1. #58none of 8172.8%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #195default of 26561.8%
  2. #232none of 26548.1%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #176default of 52373.7%
  2. #397none of 52324.0%

Leader: Kimi K3 · 88.7%

math

AIME (Vals)

82 results
  1. #25none of 8291.3%

Leader: Gemini 3.1 Pro · 98.1%

math

AIME 2025

228 results
  1. #25default of 22889.7%
  2. #128none of 22841.3%

Leader: GPT-5.2 · 99.0%

math

MGSM (Vals)

62 results
  1. #28none of 6290.9%

Leader: Opus 4.5 · 95.2%

other

Poker Agent

17 results
  1. #10none of 171034

Leader: GPT-5.2 · 1132

reasoning

ARC-AGI-1

215 results
  1. #154none of 21548.5%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #151none of 2165.3%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #180default of 5292.9%
  2. #371none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #80none of 13580.6%

Leader: Fable 5 · 88.6%

reasoning

SAGE

80 results
  1. #76none of 8029.8%

Leader: Opus 4.7 · 56.1%