priorsBuilder

Alibaba · released 2026-03-31

Qwen 3.6 Plus

Measured on 58 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. #167default of 58727.8%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #123default of 5260.9

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #26none of 19672.0%
  2. #51xhigh of 19659.0%

Leader: Opus 4.8 · 95.0%

All 58 benchmarks

show 55 more

agentic

Harvey's Legal Agent Benchmark

79 results
  1. #56max of 791.3%

Leader: Muse Spark 1.2 · 25.4%

agentic

Legal Research Bench

78 results
  1. #64max of 7814.9%

Leader: Muse Spark 1.3 · 55.3%

agentic

Tax Agent Bench

69 results
  1. #59max of 697.7%

Leader: Fable 5.1 · 49.2%

agentic

Vending-Bench 2

67 results
  1. #29max of 67$5,115

Leader: GPT-6 Astra · $15,515

agentic

τ²-Bench Telecom

393 results
  1. #8default of 39397.7%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #95default of 20620.8%

Leader: Qwen 3.8 Max · 51.3%

coding

Arena Image-to-WebDev

58 results
  1. #44max of 581472

Leader: Opus 5.5 · 1749

coding

Arena WebDev

122 results
  1. #64max of 1221461

Leader: Opus 5.5 · 1813

coding

Code Migration

77 results
  1. #63max of 7711.1%

Leader: Sonnet 5.5 · 69.8%

coding

DeepSWE v1

29 results
  1. #27max of 292.7%

Leader: GPT-5.5 · 70.0%

coding

FrontierSWE v1

17 results
  1. #17max of 1719.9%

Leader: Fable 5 · 88.2%

coding

LiveCodeBench (Vals)

127 results
  1. #25max of 12786.0%

Leader: Fable 5.1 · 90.5%

coding

ProgramBench v1 Almost Resolved

62 results
  1. #44max of 621.0%

Leader: Opus 5.5 · 65.0%

coding

ProgramBench v1 Fully Resolved

62 results
  1. #30max of 620.0%

Leader: Opus 5.5 · 18.5%

coding

ProgramBench v1 Raw Pass Rate

62 results
  1. #51max of 6228.6%

Leader: Opus 5.5 · 87.0%

coding

SWE-bench Verified (Vals)

85 results
  1. #49max of 8573.4%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #23max of 6344.9%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench 2.1 (Vals)

74 results
  1. #54max of 7453.2%

Leader: Opus 5.5 · 87.6%

coding

Terminal-Bench Hard-AA

387 results
  1. #39default of 38743.9%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #95default of 23861.4%

Leader: Fable 5.1 · 91.4%

coding

Vibe Code Bench v1.1

105 results
  1. #67max of 10525.6%

Leader: Sonnet 5.5 · 92.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #142default of 61027.0

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #74max of 2201443

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #84max of 2201445

Leader: Gemini 4 · 1553

composite

Vals Multimodal Index v1.2

33 results
  1. #25max of 3351.5%

Leader: Fable 5 · 74.2%

creative

VoxelBench (text)

55 results
  1. #43max of 551336

Leader: GPT-6 Astra · 2732

economics

CorpFin (Vals)

117 results
  1. #52max of 11761.9%

Leader: Opus 5 · 73.2%

economics

Excel Modeling Benchmark

74 results
  1. #61max of 7432.9%

Leader: Fable 5.1 · 76.7%

economics

Finance Agent v2

78 results
  1. #61max of 7840.8%

Leader: Gemini 4 · 65.4%

economics

GDPval-AA v2.1

288 results
  1. #163default of 288990

Leader: Opus 5.5 · 1866

economics

MortgageTax (Vals)

84 results
  1. #21max of 8468.0%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #32max of 12574.7%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #34default of 39975.2%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #210default of 52626.4%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #61default of 52665.4%

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

knowledge

CaseLaw (Vals)

53 results
  1. #49max of 5351.4%

Leader: Grok 4.3 · 79.3%

knowledge

GPQA Diamond

539 results
  1. #91default of 53988.2%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #39max of 12287.4%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedCode

94 results
  1. #69max of 9436.9%

Leader: Opus 5 · 63.6%

knowledge

MedScribe

96 results
  1. #64max of 9677.0%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #24max of 12287.7%

Leader: Fable 5.1 · 92.4%

knowledge

MMMU Pro (Vals)

81 results
  1. #27max of 8184.2%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #75default of 26578.0%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #113default of 52378.3%

Leader: Kimi K3 · 88.7%

math

AIME (Vals)

82 results
  1. #13max of 8294.6%

Leader: Gemini 3.1 Pro · 98.1%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #59max of 11538.2%
  2. #69none of 11532.3%

Leader: GPT-6.1 Sol · 93.7%

reasoning

CritPt

529 results
  1. #177default of 5292.9%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #36max of 13584.2%

Leader: Fable 5 · 88.6%

reasoning

SAGE

80 results
  1. #42max of 8044.9%

Leader: Opus 4.7 · 56.1%

reliability

Tool-call error rate

171 results
  1. #106max of 1712.2%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #50max of 18199.9%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #165default of 3512.1s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #281default of 35155.7

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #63max of 1771.0s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #138max of 17642.0

Leader: Muse Spark 1.1 · 204.3