Muse Spark 1.2

Composite indexes

• Artificial Analysis Intelligence Index#22 of 142
  40independentAA Intelligence Index v4.3.2, xhighArtificial Analysis: Muse Spark 1.2 (xhigh) ↗

  Leader: Claude Opus 5.5 at 58

Coding

• Terminal-Bench 4.0#33 of 88
  7.1%independentTerminal-Bench 4.0 (AA harness), xhighArtificial Analysis: Muse Spark 1.2 (xhigh) ↗

  Leader: Claude Mythos 5.1 at 60.9%

• SciCode#14 of 94
  57.4%independentxhighArtificial Analysis: Muse Spark 1.2 (xhigh) ↗

  Leader: Claude Opus 5.5 at 66.9%

Agents and tool use

• GDPval-AA#21 of 103
  1482independentGDPval-AA, xhighArtificial Analysis: Muse Spark 1.2 (xhigh) ↗

  Leader: Claude Opus 5.5 at 1846

Reasoning and knowledge

• Humanity’s Last Exam#19 of 147
  45.5%independentno tools (AA), xhighArtificial Analysis: Muse Spark 1.2 (xhigh) ↗

  Leader: Claude Opus 5.5 at 61.4%

• GPQA Diamond#37 of 142
  90.4%independentAA, xhighArtificial Analysis: Muse Spark 1.2 (xhigh) ↗

  Leader: GPT-6 Astra at 96.1%

• CritPt#22 of 139
  17.7%independentxhighArtificial Analysis: Muse Spark 1.2 (xhigh) ↗

  Leader: GPT-5.6 Sol at 32.3%

Vision and long context

• AA Long Context Reasoning#42 of 139
  79%independentxhighArtificial Analysis: Muse Spark 1.2 (xhigh) ↗

  Leader: Kimi K3 at 88.7%

Human preference

• LMArena Text#2 of 54
  1500independentmuse-spark-1.2 (xHigh), style control default, vote cutoff 2026-09-13LMArena Text leaderboard ↗

  Leader: Claude Fable 5 at 1506

• LMArena WebDev#31 of 54
  1534independentmuse-spark-1.2 xHigh, LMArena Code arena (formerly WebDev), vote cutoff 2026-09-23LMArena Code (WebDev) leaderboard ↗

  Leader: Claude Opus 5.5 at 1818

Other published results