Skip to content

Benchmarks

Sources
8
Entries tracked
22,308
Last sync
30 min
All sources syncing normally
  • Arena · Text30 minutes ago
  • Arena · WebDev30 minutes ago
  • Arena · Vision30 minutes ago
  • Arena · Agent30 minutes ago
  • GPQA Diamond54 minutes ago
  • SWE-bench54 minutes ago
  • Terminal-Bench54 minutes ago
  • ARC-AGI-254 minutes ago

Muse Spark

76±5

69interval80

metaSep 2026swing #16–#40

Overall ×1WebDev Arena ×1Vision Arena ×1Factuality Arena ×1Search Arena ×1Document Arena ×1Agent Arena ×1GPQA Diamond ×1AIME (math) ×1FrontierMath ×1SimpleQA Verified ×1ARC-AGI-2 ×1Humanity's Last Exam ×1SimpleBench ×1LiveBench ×1BFCL v4 (function calling) ×1dormantSWE-bench Verified (live board) ×1Terminal-Bench 4.0 ×1MMLU-Pro (Artificial Analysis) ×1LiveCodeBench (Artificial Analysis) ×1IFBench (Artificial Analysis) ×1HHEM Hallucination (Vectara) ×15 of 1034 models
ModelOrgIntervalSwingiiiiiiiiiiiiiiiiiiiiiiAdd to compare
16Muse SparkmetaSep 2026—75.6 84.1Ranked 75.6 = (9 × 84.1 + 3 × 50) ÷ 12. 84.1 is the mean percentile over the 9 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.69–80369/22#16–4097—9684—61—807188——87———————94—
32Muse Spark 1.3 (Max)metaSep 2026$1.25 / $4.2570.4 78.1Ranked 70.4 = (8 × 78.1 + 3 × 50) ÷ 11. 78.1 is the mean percentile over the 8 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.63–75818/22#13–3398939492—6375—93————————17————
36Muse Spark 1.2 (xHigh)metaOct 2026$1.25 / $4.2569.7 78.2Ranked 69.7 = (7 × 78.2 + 3 × 50) ÷ 10. 78.2 is the mean percentile over the 7 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.67–72817/22#13–11298719594——16———82——92————————
64Muse Spark 1.1metaSep 2026$1.25 / $4.2565.7 72.5Ranked 65.7 = (7 × 72.5 + 3 × 50) ÷ 10. 72.5 is the mean percentile over the 7 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.62–69837/22#21–11597738578—7915———79———————————
309Muse Spark Open (Max)metaOct 2026—53.7 64.7Ranked 53.7 = (1 × 64.7 + 3 × 50) ÷ 4. 64.7 is the mean percentile over the 1 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.52–55—1/22low#53–309—65————————————————————

Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model

The few things in AI and quantum that actually mattered this week — honestly summarised.

One email a week. Unsubscribe in one click. No tracking, no sharing.