priorsBuilder

Meta · released 2026-08-10

Muse Glimmer (High)

Measured on 25 benchmarks.

General frontier

21.6

#105 of 136 models · best at high

includes estimates: 24% of the mix is measured for this model

Your mix’s benchmarks

2 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #196high of 58722.0%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #280high of 526-32.9

Leader: Opus 5.5 · 46.4

All 25 benchmarks

show 23 more

agentic

AA-AnalystAgent

44 results
  1. #30high of 4420.0%

Leader: Gemini 3.7 Flash · 60.0%

agentic

AA-Briefcase v1.1

224 results
  1. #177high of 224477

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench-AA

219 results
  1. #152high of 2196.8%

Leader: Gemini 4 · 77.5%

agentic

EnterpriseOps-Gym-AA

50 results
  1. #35high of 5034.7%

Leader: Fable 5 · 51.1%

agentic

τ³-Banking

206 results
  1. #86high of 20623.5%

Leader: Qwen 3.8 Max · 51.3%

coding

SciCode

226 results
  1. #142high of 22644.9%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench Science-AA

46 results
  1. #46high of 460.0%

Leader: GPT-6 Astra · 63.3%

coding

Terminal-Bench v2.1-AA

238 results
  1. #117high of 23851.7%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #142high of 2160.5%

Leader: Sonnet 5.5 · 63.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #255high of 61017.5

Leader: Opus 5.5 · 57.6

cost

AA Intelligence Index Cost per Task

177 results
  1. #26high of 177$0.06

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #33high of 177$149

Leader: GPT-6 Luna · $10.63

economics

GDP.pdf

210 results
  1. #130high of 21010.0%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #186high of 288786

Leader: Opus 5.5 · 1866

knowledge

AA-Omniscience Accuracy

526 results
  1. #203high of 52627.0%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #298high of 52618.1%

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

knowledge

GPQA Diamond

539 results
  1. #157high of 53983.5%

Leader: GPT-6 Astra · 96.3%

knowledge

MMMU-Pro

265 results
  1. #108high of 26574.3%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #24high of 52383.3%

Leader: Kimi K3 · 88.7%

long-context

MLCR-AA

94 results
  1. #32high of 9420.0%

Leader: Sonnet 5.5 · 75.0%

reasoning

CritPt

529 results
  1. #188high of 5292.6%

Leader: Muse Wonder Full (Max) · 32.9%

speed

Latency (Time to First Token)

351 results
  1. #67high of 3511.0s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #116high of 351124.2

Leader: Celeris-1 · 1522.5