priorsBuilder

Meta · released 2026-07-09

Muse Spark 1.1

Measured on 63 benchmarks.

General frontier

49.3

#38 of 136 models · best at xhigh

includes estimates: 40% of the mix is measured for this model

Your mix’s benchmarks

3 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #44xhigh of 58746.2%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #39xhigh of 52628.1

Leader: Opus 5.5 · 46.4

coding

DeepSWE v1.1

70 results
  1. #47xhigh of 7053.3%

Leader: GPT-6 Astra · 74.1%

All 63 benchmarks

show 60 more

agentic

AA-Briefcase v1.1

224 results
  1. #145xhigh of 224851

Leader: Sonnet 5.5 · 1823

agentic

Agent Arena

50 results
  1. #39xhigh of 50-5.0%

Leader: Opus 5.5 · 15.5%

agentic

AutomationBench-AA

219 results
  1. #96xhigh of 21938.8%

Leader: Gemini 4 · 77.5%

agentic

Harvey's Legal Agent Benchmark

79 results
  1. #5xhigh of 7920.0%

Leader: Muse Spark 1.2 · 25.4%

agentic

Legal Research Bench

78 results
  1. #36xhigh of 7838.0%

Leader: Muse Spark 1.3 · 55.3%

agentic

OSWorld-Verified

13 results
  1. #3xhigh of 1380.7%

Leader: Fable 5 · 86.0%

agentic

SkillsBench

34 results
  1. #9xhigh of 3459.2%

Leader: DeepSeek V4.1 Flash · 69.8%

agentic

Terminal-Bench 2.1

18 results
  1. #12xhigh of 1876.2%

Leader: GPT-6 Astra · 87.4%

agentic

Time Horizon Index: KSP

13 results
  1. #13xhigh of 131.7%

Leader: Opus 5.5 · 91.3%

agentic

Vending-Bench 2

67 results
  1. #17xhigh of 67$6,520

Leader: GPT-6 Astra · $15,515

agentic

τ³-Banking

206 results
  1. #61xhigh of 20631.8%

Leader: Qwen 3.8 Max · 51.3%

coding

Arena Image-to-WebDev

58 results
  1. #30xhigh of 581540

Leader: Opus 5.5 · 1749

coding

Arena WebDev

122 results
  1. #39xhigh of 1221542

Leader: Opus 5.5 · 1813

coding

Code Migration

77 results
  1. #39xhigh of 7731.1%

Leader: Sonnet 5.5 · 69.8%

coding

LiveCodeBench (Vals)

127 results
  1. #29xhigh of 12785.9%

Leader: Fable 5.1 · 90.5%

coding

ProgramBench v1 Almost Resolved

62 results
  1. #40xhigh of 622.5%

Leader: Opus 5.5 · 65.0%

coding

ProgramBench v1 Fully Resolved

62 results
  1. #51xhigh of 620.0%

Leader: Opus 5.5 · 18.5%

coding

ProgramBench v1 Raw Pass Rate

62 results
  1. #52xhigh of 6227.1%

Leader: Opus 5.5 · 87.0%

coding

SciCode

226 results
  1. #19xhigh of 22658.8%

Leader: Opus 5.5 · 66.9%

coding

SWE Atlas-QnA

22 results
  1. #9xhigh of 2242.2%

Leader: Opus 5 · 63.2%

coding

SWE-bench Verified (Vals)

85 results
  1. #20xhigh of 8582.0%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.1 (Vals)

74 results
  1. #29xhigh of 7469.3%

Leader: Opus 5.5 · 87.6%

coding

Terminal-Bench v2.1-AA

238 results
  1. #55xhigh of 23877.9%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #95xhigh of 2166.1%

Leader: Sonnet 5.5 · 63.6%

coding

Vibe Code Bench v1.1

105 results
  1. #35xhigh of 10572.2%

Leader: Sonnet 5.5 · 92.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #97xhigh of 61033.7

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #12xhigh of 2201491

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #12xhigh of 2201497

Leader: Gemini 4 · 1553

composite

Vals Multimodal Index v1.2

33 results
  1. #11xhigh of 3366.7%

Leader: Fable 5 · 74.2%

cost

AA Intelligence Index Cost per Task

177 results
  1. #132xhigh of 177$1.38

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #130xhigh of 177$1,737

Leader: GPT-6 Luna · $10.63

creative

VoxelBench (text)

55 results
  1. #33xhigh of 551519

Leader: GPT-6 Astra · 2732

economics

CorpFin (Vals)

117 results
  1. #4xhigh of 11771.3%

Leader: Opus 5 · 73.2%

economics

Excel Modeling Benchmark

74 results
  1. #44xhigh of 7456.4%

Leader: Fable 5.1 · 76.7%

economics

Finance Agent v2

78 results
  1. #15xhigh of 7857.2%

Leader: Gemini 4 · 65.4%

economics

GDP.pdf

210 results
  1. #97xhigh of 21014.4%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #114xhigh of 2881210

Leader: Opus 5.5 · 1866

economics

MortgageTax (Vals)

84 results
  1. #34xhigh of 8466.1%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #2xhigh of 12579.7%

Leader: Muse Spark 1.2 · 80.4%

knowledge

AA-Omniscience Accuracy

526 results
  1. #52xhigh of 52652.0%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #111xhigh of 52650.0%

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

knowledge

GPQA Diamond

539 results
  1. #67xhigh of 53989.8%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #23xhigh of 12291.2%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedScribe

96 results
  1. #9xhigh of 9688.9%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #17xhigh of 12288.7%

Leader: Fable 5.1 · 92.4%

knowledge

MMMU Pro (Vals)

81 results
  1. #18xhigh of 8186.6%

Leader: Fable 5.1 · 90.6%

knowledge

Public Benefits Bench v1.1

50 results
  1. #30xhigh of 5061.3%

Leader: Opus 5 · 76.9%

long-context

AA-LCR v1.1

523 results
  1. #125xhigh of 52377.7%

Leader: Kimi K3 · 88.7%

long-context

Arena Document

43 results
  1. #18xhigh of 431465

Leader: Opus 5 · 1516

other

Arena Vision

116 results
  1. #27xhigh of 1161280

Leader: Fable 5 · 1308

reasoning

CritPt

529 results
  1. #89xhigh of 52915.1%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #26xhigh of 13585.0%

Leader: Fable 5 · 88.6%

reasoning

Roboflow Visual Reasoning

102 results
  1. #18high of 10276.6%
  2. #26low of 10274.2%

Leader: GPT-6 Astra · 91.2%

reasoning

SAGE

80 results
  1. #39xhigh of 8045.6%

Leader: Opus 4.7 · 56.1%

reliability

Tool-call error rate

171 results
  1. #49xhigh of 1710.6%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #18xhigh of 181100.0%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #299xhigh of 35130s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #144xhigh of 351110.1

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #114xhigh of 1771.7s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #1xhigh of 176204.3

Leader: this model · 204.3