Muse Glimmer

Composite indexes

• Artificial Analysis Intelligence Index#71 of 142
  18independentAA Intelligence Index v4.3.2, highArtificial Analysis: Muse Glimmer (high) ↗

  Leader: Claude Opus 5.5 at 58

Coding

• Terminal-Bench 4.0#51 of 88
  0.5%independentTerminal-Bench 4.0 (AA harness), highArtificial Analysis: Muse Glimmer (high) ↗

  Leader: Claude Mythos 5.1 at 60.9%

• Terminal-Bench 2.x#60 of 103
  51.7%independentTerminal-Bench 2.1 (AA harness), highArtificial Analysis: Muse Glimmer (high) ↗

  Leader: Claude Fable 5.1 at 91.4%

• SciCode#57 of 94
  44.9%independenthighArtificial Analysis: Muse Glimmer (high) ↗

  Leader: Claude Opus 5.5 at 66.9%

• SWE-bench Pro#24 of 31
  51.2%vendorHigh reasoningHugging Face: Muse-Glimmer-30B model card ↗

  Leader: Claude Opus 5.5 at 89.9%

• SWE-bench Verified#7 of 16
  76%vendorHigh reasoningHugging Face: Muse-Glimmer-30B model card ↗

  Leader: Claude Sonnet 5 at 85.2%

Agents and tool use

• GDPval-AA#64 of 103
  774independentGDPval-AA, highArtificial Analysis: Muse Glimmer (high) ↗

  Leader: Claude Opus 5.5 at 1846

• MCP Atlas#6 of 9
  75.5%vendorPublic set, High reasoningHugging Face: Muse-Glimmer-30B model card ↗

  Leader: Kimi K3 at 84.2%

• OSWorld-Verified#12 of 16
  65.9%vendorOSWorld-Verified, High reasoningHugging Face: Muse-Glimmer-30B model card ↗

  Leader: Kimi K3 at 84.8%

Reasoning and knowledge

• Humanity’s Last Exam#68 of 147
  22%independentno tools (AA), highArtificial Analysis: Muse Glimmer (high) ↗

  Leader: Claude Opus 5.5 at 61.4%

• GPQA Diamond#65 of 142
  83.5%independentAA, highArtificial Analysis: Muse Glimmer (high) ↗

  Leader: GPT-6 Astra at 96.1%

• CritPt#59 of 139
  2.6%independenthighArtificial Analysis: Muse Glimmer (high) ↗

  Leader: GPT-5.6 Sol at 32.3%

• AIME 2026#5 of 13
  94.7%vendorHigh reasoningHugging Face: Muse-Glimmer-30B model card ↗

  Leader: ERNIE 5.1 at 99.6%

Vision and long context

• AA Long Context Reasoning#12 of 139
  83.3%independenthighArtificial Analysis: Muse Glimmer (high) ↗

  Leader: Kimi K3 at 88.7%

• MMMU-Pro#39 of 72
  74.3%independentAA, highArtificial Analysis: Muse Glimmer (high) ↗

  Leader: Claude Opus 5.5 at 87.7%

Human preference

• LMArena Text#44 of 54
  1427independentmuse-glimmer, style control default, vote cutoff 2026-09-13LMArena Text leaderboard ↗

  Leader: Claude Fable 5 at 1506

• LMArena WebDev#50 of 54
  1360independentmuse-glimmer, LMArena Code arena (formerly WebDev), vote cutoff 2026-09-23LMArena Code (WebDev) leaderboard ↗

  Leader: Claude Opus 5.5 at 1818

Other published results