priorsBuilder

Alibaba · released 2026-08-14

Qwen 3.8 27B

Measured on 68 benchmarks across 5 reasoning efforts.

General frontier

41.1

#54 of 136 models · best at max

includes estimates: 19% of the mix is measured for this model

Reasoning efforts in your mix

max41.1#133 of 313
xhigh33.8#195 of 313
none33.3#199 of 313
low21.2#268 of 313
medium20.0#275 of 313

Your mix’s benchmarks

4 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #125xhigh of 58733.9%
  2. #250medium of 58714.1%
  3. #252low of 58714.0%
  4. #272none of 58712.1%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #172none of 526-8.0
  2. #186xhigh of 526-10.0
  3. #259low of 526-26.7
  4. #295medium of 526-36.1

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #14none of 19679.0%
  2. #126max of 19629.0%

Leader: Opus 4.8 · 95.0%

reasoning

SimpleBench

97 results
  1. #38max of 9760.2%

Leader: Opus 5.5 · 88.4%

All 68 benchmarks

show 64 more

agentic

AA-AnalystAgent

44 results
  1. #31xhigh of 4418.8%

Leader: Gemini 3.7 Flash · 60.0%

agentic

AA-Briefcase v1.1

224 results
  1. #55xhigh of 2241397
  2. #57medium of 2241377
  3. #73low of 2241273
  4. #136none of 224898

Leader: Sonnet 5.5 · 1823

agentic

Agent Arena

50 results
  1. #36max of 50-2.0%

Leader: Opus 5.5 · 15.5%

agentic

AutomationBench-AA

219 results
  1. #78xhigh of 21948.2%
  2. #94medium of 21940.3%
  3. #111low of 21930.1%
  4. #144none of 21912.4%

Leader: Gemini 4 · 77.5%

agentic

EnterpriseOps-Gym-AA

50 results
  1. #16xhigh of 5044.2%

Leader: Fable 5 · 51.1%

agentic

Harvey's Legal Agent Benchmark

79 results
  1. #15xhigh of 7911.3%

Leader: Muse Spark 1.2 · 25.4%

agentic

Legal Research Bench

78 results
  1. #40xhigh of 7836.1%

Leader: Muse Spark 1.3 · 55.3%

agentic

SkillsBench

34 results
  1. #30xhigh of 3438.1%

Leader: DeepSeek V4.1 Flash · 69.8%

agentic

Tax Agent Bench

69 results
  1. #24xhigh of 6930.9%

Leader: Fable 5.1 · 49.2%

agentic

Terminal-Bench Science (Vals)

40 results
  1. #40xhigh of 400.0%

Leader: GPT-6 Astra · 62.9%

agentic

τ³-Banking

206 results
  1. #6xhigh of 20648.0%
  2. #7medium of 20647.4%
  3. #58low of 20632.2%
  4. #100none of 20620.0%

Leader: Qwen 3.8 Max · 51.3%

coding

Arena Image-to-WebDev

58 results
  1. #23max of 581576

Leader: Opus 5.5 · 1749

coding

Arena WebDev

122 results
  1. #27max of 1221593

Leader: Opus 5.5 · 1813

coding

Code Migration

77 results
  1. #57xhigh of 7714.2%

Leader: Sonnet 5.5 · 69.8%

coding

IOI

44 results
  1. #37xhigh of 4439.1%

Leader: Gemini 4 · 100.0%

coding

LiveCodeBench (Vals)

127 results
  1. #43xhigh of 12784.0%

Leader: Fable 5.1 · 90.5%

coding

ProgramBench v1 Almost Resolved

62 results
  1. #45xhigh of 621.0%

Leader: Opus 5.5 · 65.0%

coding

ProgramBench v1 Fully Resolved

62 results
  1. #31xhigh of 620.0%

Leader: Opus 5.5 · 18.5%

coding

ProgramBench v1 Raw Pass Rate

62 results
  1. #61xhigh of 6211.2%

Leader: Opus 5.5 · 87.0%

coding

SciCode

226 results
  1. #132xhigh of 22646.6%
  2. #169low of 22640.0%
  3. #175medium of 22639.0%
  4. #191none of 22636.2%

Leader: Opus 5.5 · 66.9%

coding

SWE-bench Verified (Vals)

85 results
  1. #15xhigh of 8586.0%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.1 (Vals)

74 results
  1. #41xhigh of 7458.4%

Leader: Opus 5.5 · 87.6%

coding

Terminal-Bench Science-AA

46 results
  1. #40xhigh of 460.5%
  2. #45none of 460.0%

Leader: GPT-6 Astra · 63.3%

coding

Terminal-Bench v2.1-AA

238 results
  1. #47xhigh of 23879.8%
  2. #77low of 23867.4%
  3. #82medium of 23865.2%
  4. #123none of 23849.1%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #96xhigh of 2165.6%
  2. #100medium of 2165.1%
  3. #110low of 2162.5%
  4. #163none of 2160.0%

Leader: Sonnet 5.5 · 63.6%

coding

Vibe Code Bench v1.1

105 results
  1. #42xhigh of 10564.8%

Leader: Sonnet 5.5 · 92.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #99xhigh of 61033.7
  2. #138medium of 61027.6
  3. #149low of 61026.2
  4. #227none of 61020.2

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #83max of 2201438

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #87max of 2201441

Leader: Gemini 4 · 1553

cost

AA Intelligence Index Cost per Task

177 results
  1. #115xhigh of 177$1.01
  2. #119low of 177$1.05
  3. #121medium of 177$1.13
  4. #156none of 177$2.49

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #98low of 177$1,060
  2. #104medium of 177$1,165
  3. #113xhigh of 177$1,336
  4. #134none of 177$2,022

Leader: GPT-6 Luna · $10.63

economics

Excel Modeling Benchmark

74 results
  1. #35xhigh of 7459.7%

Leader: Fable 5.1 · 76.7%

economics

Finance Agent v2

78 results
  1. #47xhigh of 7848.6%

Leader: Gemini 4 · 65.4%

economics

GDP.pdf

210 results
  1. #86xhigh of 21016.6%
  2. #106medium of 21012.8%
  3. #126low of 21010.4%
  4. #161none of 2105.2%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #69xhigh of 2881419
  2. #77medium of 2881381
  3. #81low of 2881362
  4. #143none of 2881072

Leader: Opus 5.5 · 1866

economics

MortgageTax (Vals)

84 results
  1. #42xhigh of 8464.9%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #80xhigh of 12570.8%

Leader: Muse Spark 1.2 · 80.4%

knowledge

AA-Omniscience Accuracy

526 results
  1. #323medium of 52618.4%
  2. #354low of 52617.1%
  3. #387xhigh of 52615.6%
  4. #484none of 5268.6%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #11none of 52681.9%
  2. #43xhigh of 52669.7%
  3. #131low of 52647.1%
  4. #195medium of 52633.3%

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

knowledge

GPQA Diamond

539 results
  1. #59xhigh of 53990.5%
  2. #138medium of 53984.5%
  3. #140low of 53984.5%
  4. #175none of 53981.8%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #33xhigh of 12288.9%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedCode

94 results
  1. #89xhigh of 9428.7%

Leader: Opus 5 · 63.6%

knowledge

MedScribe

96 results
  1. #38xhigh of 9683.8%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #62xhigh of 12284.3%

Leader: Fable 5.1 · 92.4%

knowledge

MMMU Pro (Vals)

81 results
  1. #28xhigh of 8183.9%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #87xhigh of 26576.3%
  2. #110medium of 26574.2%
  3. #116low of 26573.8%
  4. #147none of 26569.9%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #47xhigh of 52382.0%
  2. #92medium of 52379.7%
  3. #130low of 52377.3%
  4. #222none of 52369.3%

Leader: Kimi K3 · 88.7%

long-context

MLCR-AA

94 results
  1. #27xhigh of 9421.7%

Leader: Sonnet 5.5 · 75.0%

math

ProofBench v1.1

52 results
  1. #46xhigh of 5216.0%

Leader: Sonnet 5.5 · 100.0%

other

Arena Vision

116 results
  1. #57max of 1161244

Leader: Fable 5 · 1308

reasoning

ARC-AGI-1

215 results
  1. #82xhigh of 21587.5%
  2. #125low of 21569.2%
  3. #126medium of 21568.7%
  4. #173none of 21534.0%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #102xhigh of 21642.4%
  2. #122low of 21622.8%
  3. #133medium of 21613.2%
  4. #184none of 2161.5%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #146xhigh of 5295.4%
  2. #269none of 5290.3%
  3. #307medium of 5290.0%
  4. #309low of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #68xhigh of 13582.4%

Leader: Fable 5 · 88.6%

reasoning

Roboflow Visual Reasoning

102 results
  1. #48high of 10266.0%
  2. #57low of 10262.0%

Leader: GPT-6 Astra · 91.2%

reasoning

SAGE

80 results
  1. #7xhigh of 8052.4%

Leader: Opus 4.7 · 56.1%

reliability

Tool-call error rate

171 results
  1. #87max of 1711.4%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #123max of 18198.8%

Leader: GPT-5 Pro · 100.0%

safety

CWE-Bench

19 results
  1. #19xhigh of 1926.7%

Leader: Grok 4.7 · 68.3%

safety

CyberBench v1.1

45 results
  1. #28xhigh of 4567.8%

Leader: Wonder · 80.4%

speed

Latency (Time to First Token)

351 results
  1. #221low of 3513.8s
  2. #222xhigh of 3513.8s
  3. #223medium of 3513.9s
  4. #225none of 3514.0s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #293low of 35152.7
  2. #296none of 35151.6
  3. #298medium of 35150.2
  4. #305xhigh of 35145.5

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #34max of 1770.7s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #99max of 17656.0

Leader: Muse Spark 1.1 · 204.3