Muse Spark 1.3

Composite indexes

• Artificial Analysis Intelligence Index#6 of 142
  48independentAA Intelligence Index v4.3.2, max effortArtificial Analysis: Muse Spark 1.3 (max) ↗

  Leader: Claude Opus 5.5 at 58

Coding

• Terminal-Bench 4.0#13 of 88
  33.3%independentTerminal-Bench 4.0 (AA harness), max effortArtificial Analysis: Muse Spark 1.3 (max) ↗

  Leader: Claude Mythos 5.1 at 60.9%

• SciCode#9 of 94
  58.8%independentmax effortArtificial Analysis: Muse Spark 1.3 (max) ↗

  Leader: Claude Opus 5.5 at 66.9%

Agents and tool use

• GDPval-AA#5 of 103
  1674independentGDPval-AA, max effortArtificial Analysis: Muse Spark 1.3 (max) ↗

  Leader: Claude Opus 5.5 at 1846

Reasoning and knowledge

• Humanity’s Last Exam#9 of 147
  48.7%independentno tools (AA), max effortArtificial Analysis: Muse Spark 1.3 (max) ↗

  Leader: Claude Opus 5.5 at 61.4%

• GPQA Diamond#11 of 142
  93.5%independentAA, max effortArtificial Analysis: Muse Spark 1.3 (max) ↗

  Leader: GPT-6 Astra at 96.1%

• CritPt#10 of 139
  24.9%independentmax effortArtificial Analysis: Muse Spark 1.3 (max) ↗

  Leader: GPT-5.6 Sol at 32.3%

Vision and long context

• AA Long Context Reasoning#14 of 139
  83%independentmax effortArtificial Analysis: Muse Spark 1.3 (max) ↗

  Leader: Kimi K3 at 88.7%

Human preference

• LMArena Text#4 of 54
  1493independentmuse-spark-1.3-max, style control default, vote cutoff 2026-09-13LMArena Text leaderboard ↗

  Leader: Claude Fable 5 at 1506

• LMArena WebDev#8 of 54
  1658independentmuse-spark-1.3-max, LMArena Code arena (formerly WebDev), vote cutoff 2026-09-23LMArena Code (WebDev) leaderboard ↗

  Leader: Claude Opus 5.5 at 1818

Other published results