priorsBuilder

Anthropic · released 2025-05-14

Opus 4

Measured on 31 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. #271default of 58712.3%
  2. #389none of 5876.2%

Leader: Opus 5.5 · 61.4%

reasoning

BullshitBench v2

196 results
  1. #114medium of 19634.0%

Leader: Opus 4.8 · 95.0%

reasoning

SimpleBench

97 results
  1. #40medium of 9758.8%

Leader: Opus 5.5 · 88.4%

All 31 benchmarks

show 28 more

agentic

τ²-Bench Telecom

393 results
  1. #147default of 39373.4%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #93default of 28263.6%
  2. #118none of 28254.2%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #89medium of 12770.2%

Leader: Fable 5.1 · 90.5%

coding

Terminal-Bench Hard-AA

387 results
  1. #109default of 38731.1%

Leader: GPT-5.6 Sol · 65.9%

composite

AA Intelligence Index v4.3.2

610 results
  1. #219default of 61020.6
  2. #268none of 61016.6

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #97medium of 2201426

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #89medium of 2201439

Leader: Gemini 4 · 1553

economics

MortgageTax (Vals)

84 results
  1. #65medium of 8458.6%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #68medium of 12571.9%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #153default of 39953.7%
  2. #223none of 39943.3%

Leader: Grok 4.3 · 83.3%

knowledge

Arena Search

28 results
  1. #27medium of 281126

Leader: GPT-5.6 Sol · 1257

knowledge

GPQA Diamond

539 results
  1. #195default of 53979.6%
  2. #287none of 53970.1%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #88medium of 12271.7%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedQA (Vals)

80 results
  1. #25medium of 8092.9%

Leader: o1 · 96.5%

knowledge

MMLU Pro (Vals)

122 results
  1. #47medium of 12286.2%

Leader: Fable 5.1 · 92.4%

knowledge

MMLU-Pro

285 results
  1. #11default of 28587.3%
  2. #22none of 28586.0%

Leader: Gemini 3 Pro · 89.8%

knowledge

MMMU Pro (Vals)

81 results
  1. #57medium of 8173.3%

Leader: Fable 5.1 · 90.6%

long-context

AA-LCR v1.1

523 results
  1. #221default of 52369.3%

Leader: Kimi K3 · 88.7%

math

AIME (Vals)

82 results
  1. #64medium of 8241.3%

Leader: Gemini 3.1 Pro · 98.1%

math

AIME 2025

228 results
  1. #77default of 22873.3%
  2. #145none of 22836.3%

Leader: GPT-5.2 · 99.0%

math

MATH 500 (Vals)

48 results
  1. #22medium of 4890.4%

Leader: Gemini 3 Pro · 96.4%

math

MATH-500

162 results
  1. #14default of 16298.2%
  2. #42none of 16294.1%

Leader: GPT-5 · 99.4%

math

MGSM (Vals)

62 results
  1. #6medium of 6293.8%

Leader: Opus 4.5 · 95.2%

other

Arena Vision

116 results
  1. #76medium of 1161208

Leader: Fable 5 · 1308

other

T3 Code usage share

85 results
  1. #47medium of 850.0%

Leader: Opus 5.5 · 29.1%

reasoning

ARC-AGI-1

215 results
  1. #170medium of 21535.7%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #142medium of 2168.6%

Leader: GPT-6 Astra · 95.0%

reasoning

LegalBench

135 results
  1. #59medium of 13583.1%

Leader: Fable 5 · 88.6%