Muse Spark 1.1

Composite indexes

• Artificial Analysis Intelligence Index#35 of 142
  34independentAA Intelligence Index v4.3.2, xhighArtificial Analysis: Muse Spark 1.1 (xhigh) ↗

  Leader: Claude Opus 5.5 at 58

Coding

• Terminal-Bench 4.0#36 of 88
  6.1%independentTerminal-Bench 4.0 (AA harness), xhighArtificial Analysis: Muse Spark 1.1 (xhigh) ↗

  Leader: Claude Mythos 5.1 at 60.9%

• SciCode#10 of 94
  58.8%independentxhighArtificial Analysis: Muse Spark 1.1 (xhigh) ↗

  Leader: Claude Opus 5.5 at 66.9%

Agents and tool use

• GDPval-AA#38 of 103
  1208independentGDPval-AA, xhighArtificial Analysis: Muse Spark 1.1 (xhigh) ↗

  Leader: Claude Opus 5.5 at 1846

Reasoning and knowledge

• Humanity’s Last Exam#18 of 147
  46.2%independentno tools (AA), xhighArtificial Analysis: Muse Spark 1.1 (xhigh) ↗

  Leader: Claude Opus 5.5 at 61.4%

• GPQA Diamond#40 of 142
  89.8%independentAA, xhighArtificial Analysis: Muse Spark 1.1 (xhigh) ↗

  Leader: GPT-6 Astra at 96.1%

• CritPt#31 of 139
  15.1%independentxhighArtificial Analysis: Muse Spark 1.1 (xhigh) ↗

  Leader: GPT-5.6 Sol at 32.3%

Vision and long context

• AA Long Context Reasoning#48 of 139
  77.7%independentxhighArtificial Analysis: Muse Spark 1.1 (xhigh) ↗

  Leader: Kimi K3 at 88.7%

Human preference

• LMArena Text#5 of 54
  1493independentmuse-spark-1.1, style control default, vote cutoff 2026-09-13LMArena Text leaderboard ↗

  Leader: Claude Fable 5 at 1506

• LMArena WebDev#28 of 54
  1542independentmuse-spark-1.1, LMArena Code arena (formerly WebDev), vote cutoff 2026-09-23LMArena Code (WebDev) leaderboard ↗

  Leader: Claude Opus 5.5 at 1818

Other published results