priorsBuilder

Anthropic · released 2025-05-14

Sonnet 4

Measured on 46 benchmarks.

General frontier

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

Your mix’s benchmarks

4 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #303default of 58710.7%
  2. #499none of 5874.3%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #131default of 5260.2
  2. #179none of 526-9.0

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #125high of 19630.0%
  2. #127none of 19629.0%

Leader: Opus 4.8 · 95.0%

reasoning

SimpleBench

97 results
  1. #61high of 9745.5%

Leader: Opus 5.5 · 88.4%

All 46 benchmarks

show 42 more

agentic

τ²-Bench Telecom

393 results
  1. #175default of 39364.6%
  2. #197none of 39352.3%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #112default of 20616.7%

Leader: Qwen 3.8 Max · 51.3%

coding

LiveCodeBench

282 results
  1. #83default of 28265.5%
  2. #140none of 28244.9%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #97high of 12762.4%

Leader: Fable 5.1 · 90.5%

coding

Terminal-Bench Hard-AA

387 results
  1. #110default of 38731.1%
  2. #128none of 38727.3%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #147default of 23836.3%

Leader: Fable 5.1 · 91.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #239default of 61018.9
  2. #269none of 61016.6

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #121high of 2201402

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #104high of 2201421

Leader: Gemini 4 · 1553

economics

CorpFin (Vals)

117 results
  1. #56high of 11761.2%

Leader: Opus 5 · 73.2%

economics

GDPval-AA v2.1

288 results
  1. #199default of 288691

Leader: Opus 5.5 · 1866

economics

MortgageTax (Vals)

84 results
  1. #51high of 8462.5%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #66high of 12572.0%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #148default of 39954.7%
  2. #205none of 39945.4%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #258default of 52622.7%
  2. #259none of 52622.7%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #37default of 52670.9%
  2. #79none of 52659.0%

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

knowledge

GPQA Diamond

539 results
  1. #214default of 53977.7%
  2. #305none of 53968.3%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #80high of 12275.0%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedCode

94 results
  1. #71high of 9435.0%

Leader: Opus 5 · 63.6%

knowledge

MedQA (Vals)

80 results
  1. #26high of 8092.7%

Leader: o1 · 96.5%

knowledge

MedScribe

96 results
  1. #78high of 9672.4%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #67high of 12283.9%

Leader: Fable 5.1 · 92.4%

knowledge

MMLU-Pro

285 results
  1. #37default of 28584.2%
  2. #43none of 28583.7%

Leader: Gemini 3 Pro · 89.8%

knowledge

MMMU Pro (Vals)

81 results
  1. #55high of 8174.9%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #186none of 26562.4%
  2. #194default of 26561.8%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #209default of 52370.3%
  2. #324none of 52344.0%

Leader: Kimi K3 · 88.7%

math

AIME (Vals)

82 results
  1. #50high of 8276.3%

Leader: Gemini 3.1 Pro · 98.1%

math

AIME 2025

228 results
  1. #74default of 22874.3%
  2. #139none of 22838.0%

Leader: GPT-5.2 · 99.0%

math

MATH 500 (Vals)

48 results
  1. #16high of 4893.8%

Leader: Gemini 3 Pro · 96.4%

math

MATH-500

162 results
  1. #5default of 16299.1%
  2. #44none of 16293.4%

Leader: GPT-5 · 99.4%

math

MGSM (Vals)

62 results
  1. #9high of 6293.0%

Leader: Opus 4.5 · 95.2%

other

Arena Vision

116 results
  1. #77high of 1161206

Leader: Fable 5 · 1308

other

T3 Code usage share

85 results
  1. #53high of 850.0%

Leader: Opus 5.5 · 29.1%

reasoning

ARC-AGI-1

215 results
  1. #164high of 21540.0%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #149high of 2165.9%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #225none of 5291.1%
  2. #271default of 5290.3%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #62high of 13583.0%

Leader: Fable 5 · 88.6%

reasoning

SAGE

80 results
  1. #66high of 8035.0%

Leader: Opus 4.7 · 56.1%

reliability

Tool-call error rate

172 results
  1. #107high of 1722.1%

Leader: Gemini 4 · 0.0%

reliability

Uptime (7d)

182 results
  1. #23high of 182100.0%

Leader: GPT-5 Pro · 100.0%

speed

Provider latency

178 results
  1. #98high of 1781.4s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #141high of 17641.0

Leader: Muse Spark 1.1 · 204.5