priorsBuilder

Anthropic · released 2026-02-05

Opus 4.6

Measured on 66 benchmarks.

General frontier

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

Your mix’s benchmarks

6 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #82max of 58739.9%
  2. #215high of 58719.1%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #85max of 52613.7
  2. #115high of 5262.4

Leader: Opus 5.5 · 46.4

reasoning

ARC-AGI-3

57 results
  1. #35max of 570.5%

Leader: GPT-6 Astra · 99.9%

reasoning

BullshitBench v2

196 results
  1. #7high of 19687.0%
  2. #8none of 19683.0%

Leader: Opus 4.8 · 95.0%

math

FrontierMath Tier 4 (v2)

70 results
  1. #41max of 7026.8%

Leader: GPT-6.1 Sol · 100.0%

reasoning

SimpleBench

97 results
  1. #22max of 9767.6%

Leader: Opus 5.5 · 88.4%

All 66 benchmarks

show 60 more

agentic

APEX-Agents-AA

33 results
  1. #10max of 3333.0%

Leader: Gemini 3.5 Flash · 47.1%

agentic

Terminal-Bench 2.0

40 results
  1. #5max of 4076.4%

Leader: GPT-5.5 · 84.7%

agentic

Vending-Bench 2

67 results
  1. #13max of 67$8,018

Leader: GPT-6 Astra · $15,515

agentic

Vending-Bench Arena

12 results
  1. #11max of 12$4,053

Leader: GPT-6 Astra · $12,400

agentic

τ²-Bench Telecom

393 results
  1. #52max of 39392.1%
  2. #100high of 39384.8%

Leader: GLM 5.2 · 99.1%

coding

Arena Image-to-WebDev

58 results
  1. #28high of 581543
  2. #32max of 581539

Leader: Opus 5.5 · 1749

coding

Arena WebDev

122 results
  1. #38high of 1221547
  2. #43max of 1221537

Leader: Opus 5.5 · 1813

coding

DeepSWE v1

29 results
  1. #16max of 2927.6%

Leader: GPT-5.5 · 70.0%

coding

FrontierCode 1.1 Extended

130 results
  1. #103high of 13043.7%
  2. #113medium of 13038.6%
  3. #118low of 13032.9%

Leader: Opus 5.5 · 65.3%

coding

FrontierCode 1.1 Main

130 results
  1. #106high of 13026.6%
  2. #113medium of 13023.7%
  3. #120low of 13018.3%

Leader: Opus 5.5 · 54.6%

coding

FrontierSWE v1

17 results
  1. #9max of 1748.9%

Leader: Fable 5 · 88.2%

coding

LiveCodeBench (Vals)

127 results
  1. #38max of 12784.7%

Leader: Fable 5.1 · 90.5%

coding

SWE Atlas-QnA

22 results
  1. #13max of 2233.3%

Leader: Opus 5 · 63.2%

coding

SWE-bench Verified (Vals)

85 results
  1. #30max of 8578.2%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #11max of 6358.4%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench Hard-AA

387 results
  1. #26high of 38748.5%
  2. #30max of 38746.2%

Leader: GPT-5.6 Sol · 65.9%

coding

Vibe Code Bench v1.1

105 results
  1. #47max of 10557.6%

Leader: Sonnet 5.5 · 92.4%

coding

WeirdML v2

127 results
  1. #19max of 12777.9%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #109max of 61031.9
  2. #147high of 61026.4

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #3high of 2201504
  2. #7max of 2201498

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #2high of 2201518
  2. #6max of 2201512

Leader: Gemini 4 · 1553

creative

MineBench

72 results
  1. #37max of 721521

Leader: GPT-6 Astra Pro · 2281

creative

VoxelBench (image)

16 results
  1. #5max of 161441

Leader: GPT-6.1 Sol · 2214

creative

VoxelBench (text)

55 results
  1. #39max of 551411

Leader: GPT-6 Astra · 2732

economics

CorpFin (Vals)

117 results
  1. #14max of 11767.0%

Leader: Opus 5 · 73.2%

economics

MortgageTax (Vals)

84 results
  1. #15max of 8468.5%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #8max of 12576.0%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #156max of 39953.1%
  2. #208high of 39944.6%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #76max of 52647.0%
  2. #82high of 52645.8%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #171max of 52637.2%
  2. #274high of 52619.9%

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

knowledge

Arena Search

28 results
  1. #2max of 281253

Leader: GPT-5.6 Sol · 1257

knowledge

CaseLaw (Vals)

53 results
  1. #20max of 5362.1%

Leader: Grok 4.3 · 79.3%

knowledge

Global-MMLU-Lite

118 results
  1. #4max of 11892.2%
  2. #8high of 11890.6%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #72max of 53989.6%
  2. #151high of 53984.0%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #29max of 12289.6%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedCode

94 results
  1. #25max of 9449.1%

Leader: Opus 5 · 63.6%

knowledge

MedQA (Vals)

80 results
  1. #12max of 8095.4%

Leader: o1 · 96.5%

knowledge

MedScribe

96 results
  1. #20max of 9686.7%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #15max of 12289.1%

Leader: Fable 5.1 · 92.4%

knowledge

MMMU Pro (Vals)

81 results
  1. #29max of 8183.9%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #95max of 26575.4%
  2. #128high of 26572.5%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #119max of 52378.0%
  2. #235high of 52367.0%

Leader: Kimi K3 · 88.7%

long-context

Arena Document

43 results
  1. #3high of 431507
  2. #4max of 431507

Leader: Opus 5 · 1516

math

AIME (Vals)

82 results
  1. #9max of 8295.6%

Leader: Gemini 3.1 Pro · 98.1%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #30max of 11566.0%

Leader: GPT-6.1 Sol · 93.7%

other

Arena Vision

116 results
  1. #3high of 1161299
  2. #7max of 1161294

Leader: Fable 5 · 1308

other

T3 Code usage share

85 results
  1. #15max of 850.1%

Leader: Opus 5.5 · 29.1%

reasoning

ARC-AGI-1

215 results
  1. #40high of 21594.0%
  2. #45max of 21593.0%
  3. #53medium of 21592.0%
  4. #93low of 21586.0%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #53high of 21669.2%
  2. #55max of 21668.8%
  3. #63medium of 21666.3%
  4. #67low of 21664.6%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #101max of 52912.6%
  2. #181high of 5292.8%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

Furniture Assembly

31 results
  1. #23max of 3128.3%

Leader: Opus 5.5 · 83.3%

reasoning

LegalBench

135 results
  1. #21max of 13585.3%

Leader: Fable 5 · 88.6%

reasoning

SAGE

80 results
  1. #12max of 8051.6%

Leader: Opus 4.7 · 56.1%

reasoning

SimpleQA Verified

47 results
  1. #17max of 4745.2%

Leader: Gemini 3.1 Pro · 77.5%

reliability

Tool-call error rate

171 results
  1. #57max of 1710.7%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #139max of 18198.4%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #140high of 3511.8s
  2. #287max of 35123s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #316max of 35142.7
  2. #328high of 35138.2

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #118max of 1771.8s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #145max of 17638.3

Leader: Muse Spark 1.1 · 204.3