priorsBuilder

Anthropic · released 2025-11-24

Opus 4.5

Measured on 69 benchmarks.

General frontier

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

Your mix’s benchmarks

5 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #145default of 58730.1%
  2. #264none of 58713.2%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #83default of 52614.0
  2. #152none of 526-4.1

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #5high of 19690.0%
  2. #13none of 19679.0%

Leader: Opus 4.8 · 95.0%

math

FrontierMath Tier 4 (v2)

70 results
  1. #62high of 704.9%

Leader: GPT-6.1 Sol · 100.0%

reasoning

SimpleBench

97 results
  1. #30high of 9762.0%

Leader: Opus 5.5 · 88.4%

All 69 benchmarks

show 64 more

agentic

Terminal-Bench 2.0

40 results
  1. #10high of 4063.1%

Leader: GPT-5.5 · 84.7%

agentic

Vending-Bench 2

67 results
  1. #33high of 67$4,967

Leader: GPT-6 Astra · $15,515

agentic

WeirdML v3

17 results
  1. #15high of 176.5%

Leader: GPT-6 Astra · 42.2%

agentic

τ²-Bench Telecom

393 results
  1. #68default of 39389.5%
  2. #89none of 39386.3%

Leader: GLM 5.2 · 99.1%

coding

Arena WebDev

122 results
  1. #56high of 1221494

Leader: Opus 5.5 · 1813

coding

Drone-Bench

11 results
  1. #8high of 1159.2%

Leader: Opus 5.5 · 97.3%

coding

LiveCodeBench

282 results
  1. #8default of 28287.1%
  2. #46none of 28273.8%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #47high of 12783.7%

Leader: Fable 5.1 · 90.5%

coding

SWE-bench Verified (Vals)

85 results
  1. #36high of 8576.4%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #10high of 6358.4%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench Hard-AA

387 results
  1. #28default of 38747.0%
  2. #56none of 38740.9%

Leader: GPT-5.6 Sol · 65.9%

coding

Vibe Code Bench v1.1

105 results
  1. #72high of 10520.6%

Leader: Sonnet 5.5 · 92.4%

coding

WeirdML v2

127 results
  1. #37high of 12763.7%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #126default of 61029.1
  2. #180none of 61023.7

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #40high of 2201474

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #26high of 2201486

Leader: Gemini 4 · 1553

composite

Vals RSI Index v1.1

24 results
  1. #23high of 2414.8%

Leader: Opus 5.5 · 37.3%

composite

Vals RSI Index v1.1: Harness Engineering: Judge

24 results
  1. #5high of 2419.0%

Leader: GPT-6 Sol · 22.8%

composite

Vals RSI Index v1.1: Post-training: Finance Agent

24 results
  1. #15high of 240.0%

Leader: Opus 5.5 · 35.1%

composite

Vals RSI Index v1.1: Pre-training: Compression

24 results
  1. #23high of 2422.3%

Leader: Opus 5.5 · 46.5%

composite

Vals RSI Index v1.1: Pre-training: LM Training

24 results
  1. #24high of 2418.0%

Leader: Opus 5.5 · 53.0%

creative

MineBench

72 results
  1. #45high of 721356

Leader: GPT-6 Astra Pro · 2281

creative

threejseval

34 results
  1. #32high of 341155

Leader: Opus 5.5 · 2079

creative

VoxelBench (image)

16 results
  1. #8high of 161287

Leader: GPT-6.1 Sol · 2214

creative

VoxelBench (text)

55 results
  1. #40high of 551408

Leader: GPT-6 Astra · 2732

economics

CorpFin (Vals)

117 results
  1. #35high of 11765.1%

Leader: Opus 5 · 73.2%

economics

MortgageTax (Vals)

84 results
  1. #14high of 8468.7%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #28high of 12574.9%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #131default of 39958.0%
  2. #227none of 39943.0%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #78default of 52646.6%
  2. #115none of 52640.9%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #161default of 52639.0%
  2. #250none of 52623.8%

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

knowledge

Arena Search

28 results
  1. #17high of 281180

Leader: GPT-5.6 Sol · 1257

knowledge

CaseLaw (Vals)

53 results
  1. #18high of 5362.6%

Leader: Grok 4.3 · 79.3%

knowledge

Global-MMLU-Lite

118 results
  1. #6default of 11891.3%
  2. #9none of 11890.6%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #110default of 53986.6%
  2. #183none of 53981.0%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #45high of 12285.9%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedCode

94 results
  1. #24high of 9449.2%

Leader: Opus 5 · 63.6%

knowledge

MedQA (Vals)

80 results
  1. #10high of 8095.9%

Leader: o1 · 96.5%

knowledge

MedScribe

96 results
  1. #27high of 9685.3%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #31high of 12287.3%

Leader: Fable 5.1 · 92.4%

knowledge

MMLU-Pro

285 results
  1. #3default of 28589.5%
  2. #5none of 28588.9%

Leader: Gemini 3 Pro · 89.8%

knowledge

MMMU Pro (Vals)

81 results
  1. #36high of 8182.9%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #111default of 26574.0%
  2. #134none of 26571.2%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #129default of 52377.3%
  2. #205none of 52370.7%

Leader: Kimi K3 · 88.7%

long-context

Arena Document

43 results
  1. #21high of 431462

Leader: Opus 5 · 1516

math

AIME (Vals)

82 results
  1. #12high of 8295.4%

Leader: Gemini 3.1 Pro · 98.1%

math

AIME 2025

228 results
  1. #19default of 22891.3%
  2. #97none of 22862.7%

Leader: GPT-5.2 · 99.0%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #65high of 11534.4%

Leader: GPT-6.1 Sol · 93.7%

math

MGSM (Vals)

62 results
  1. #1high of 6295.2%

Leader: this model · 95.2%

other

Poker Agent

17 results
  1. #11high of 171033

Leader: GPT-5.2 · 1132

other

T3 Code usage share

85 results
  1. #24high of 850.0%

Leader: Opus 5.5 · 29.1%

reasoning

ARC-AGI-1

215 results
  1. #105high of 21580.0%
  2. #165none of 21540.0%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #106high of 21637.6%
  2. #143none of 2167.8%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #158default of 5294.6%
  2. #265none of 5290.3%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

Furniture Assembly

31 results
  1. #24high of 3128.3%

Leader: Opus 5.5 · 83.3%

reasoning

LegalBench

135 results
  1. #30high of 13584.6%

Leader: Fable 5 · 88.6%

reasoning

SAGE

80 results
  1. #8high of 8052.1%

Leader: Opus 4.7 · 56.1%

reasoning

SimpleQA Verified

47 results
  1. #23high of 4739.0%

Leader: Gemini 3.1 Pro · 77.5%

reliability

Tool-call error rate

171 results
  1. #55high of 1710.7%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #65high of 18199.8%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #80none of 3511.1s
  2. #276default of 35119s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #287default of 35154.3
  2. #302none of 35146.3

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #96high of 1771.4s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #103high of 17654.9

Leader: Muse Spark 1.1 · 204.3