priorsBuilder

xAI · released 2025-02-19

Grok 3

Measured on 34 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. #520none of 5874.1%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #283none of 526-33.2

Leader: Opus 5.5 · 46.4

reasoning

SimpleBench

97 results
  1. #71none of 9736.1%

Leader: Opus 5.5 · 88.4%

All 34 benchmarks

show 31 more

agentic

τ²-Bench Telecom

393 results
  1. #204none of 39348.8%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #144none of 28242.5%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #104none of 12752.9%

Leader: Fable 5.1 · 90.5%

coding

Terminal-Bench Hard-AA

387 results
  1. #212none of 38711.4%

Leader: GPT-5.6 Sol · 65.9%

coding

WeirdML v2

127 results
  1. #99none of 12737.2%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #329none of 61012.1
  2. #366default of 61010.4

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #113none of 2201411

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #116none of 2201410

Leader: Gemini 4 · 1553

economics

CorpFin (Vals)

117 results
  1. #73none of 11759.7%

Leader: Opus 5 · 73.2%

economics

TaxEval (Vals)

125 results
  1. #10none of 12575.9%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #192none of 39946.9%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #188none of 52628.9%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #361none of 52612.7%

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

knowledge

GPQA Diamond

539 results
  1. #296none of 53969.3%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #83none of 12274.2%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedQA (Vals)

80 results
  1. #53none of 8083.8%

Leader: o1 · 96.5%

knowledge

MMLU Pro (Vals)

122 results
  1. #86none of 12279.9%

Leader: Fable 5.1 · 92.4%

knowledge

MMLU-Pro

285 results
  1. #98none of 28579.9%

Leader: Gemini 3 Pro · 89.8%

long-context

AA-LCR v1.1

523 results
  1. #279none of 52358.0%

Leader: Kimi K3 · 88.7%

math

AIME (Vals)

82 results
  1. #55none of 8258.8%

Leader: Gemini 3.1 Pro · 98.1%

math

AIME 2025

228 results
  1. #105none of 22858.0%

Leader: GPT-5.2 · 99.0%

math

MATH 500 (Vals)

48 results
  1. #24none of 4889.8%

Leader: Gemini 3 Pro · 96.4%

math

MATH-500

162 results
  1. #70none of 16287.0%

Leader: GPT-5 · 99.4%

math

MGSM (Vals)

62 results
  1. #23none of 6291.3%

Leader: Opus 4.5 · 95.2%

reasoning

ARC-AGI-1

215 results
  1. #204none of 2155.5%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #209none of 2160.0%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #354none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #65none of 13582.6%

Leader: Fable 5 · 88.6%

reasoning

SimpleQA Verified

47 results
  1. #21none of 4739.3%

Leader: Gemini 3.1 Pro · 77.5%

speed

Latency (Time to First Token)

351 results
  1. #117none of 3511.6s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #135none of 351112.1

Leader: Celeris-1 · 1522.5