priorsBuilder

Anthropic · released 2024-10-22

Haiku 3.5

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. #558none of 5873.6%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #247none of 526-22.5

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #74medium of 19650.0%

Leader: Opus 4.8 · 95.0%

All 31 benchmarks

show 28 more

agentic

τ²-Bench Telecom

393 results
  1. #295none of 39324.6%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #177none of 28231.4%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #114medium of 12741.9%

Leader: Fable 5.1 · 90.5%

coding

Terminal-Bench Hard-AA

387 results
  1. #306none of 3872.3%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #197none of 23810.1%

Leader: Fable 5.1 · 91.4%

coding

WeirdML v2

127 results
  1. #110medium of 12730.7%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #406none of 6108.9

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #168medium of 2201325

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #162medium of 2201328

Leader: Gemini 4 · 1553

economics

CorpFin (Vals)

117 results
  1. #95medium of 11750.8%

Leader: Opus 5 · 73.2%

economics

GDPval-AA v2.1

288 results
  1. #250none of 288210

Leader: Opus 5.5 · 1866

economics

TaxEval (Vals)

125 results
  1. #119medium of 12557.4%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #231none of 39942.8%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #434none of 52613.2%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #80none of 52658.9%

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

knowledge

GPQA Diamond

539 results
  1. #458none of 53940.8%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #116medium of 12237.9%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MMLU Pro (Vals)

122 results
  1. #116medium of 12264.1%

Leader: Fable 5.1 · 92.4%

knowledge

MMLU-Pro

285 results
  1. #211none of 28563.4%

Leader: Gemini 3 Pro · 89.8%

knowledge

MMMU-Pro

265 results
  1. #237none of 26545.6%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #386none of 52327.3%

Leader: Kimi K3 · 88.7%

math

AIME (Vals)

82 results
  1. #80medium of 823.3%

Leader: Gemini 3.1 Pro · 98.1%

math

MATH 500 (Vals)

48 results
  1. #46medium of 4864.2%

Leader: Gemini 3 Pro · 96.4%

math

MATH-500

162 results
  1. #109none of 16272.1%

Leader: GPT-5 · 99.4%

math

MGSM (Vals)

62 results
  1. #56medium of 6284.6%

Leader: Opus 4.5 · 95.2%

other

Arena Vision

116 results
  1. #105medium of 1161127

Leader: Fable 5 · 1308

reasoning

CritPt

529 results
  1. #403none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #112medium of 13570.3%

Leader: Fable 5 · 88.6%