⌕Is ___ SOTA?
isitsota / categories / Factuality
Factuality · Oct 13, 2026
Who is SOTA in Factuality?
Muse Spark 1.1

Short-form factual accuracy. SimpleQA Verified plus the LMArena factuality slice. As of Oct 13, 2026, Muse Spark 1.1 holds Factuality. Muse Spark 1.1 is SOTA in Factuality since 2026-07-20. No eligible model is credibly ahead on the…

OverallOpen weights≤ 32BBest per $
Standings · overall

The board

History →
#ModelStateConfidenceWhy
1GGemini 4 Argon
Google DeepMind		Not SOTA · #1mediumRanked #1 in Factuality.
1MMuse Spark 1.1
Meta		SOTAmediumMuse Spark 1.1 is SOTA in Factuality since 2026-07-20. No eligible model is credibly ahead on the weighted primary evidence.
2AClaude Opus 5.5
Anthropic		Not SOTA · #2mediumRanked #2 in Factuality.
3AClaude Fable 5.1
Anthropic		Near-SOTAmediumClose in Factuality: rank #3, 25.0 percentile points behind the leader.
4AClaude Opus 4.6
Anthropic		Not SOTA · #4mediumRanked #4 in Factuality.
5AClaude Opus 5
Anthropic		Not SOTA · #5mediumRanked #5 in Factuality.
6OGPT-5.5
OpenAI		Not SOTA · #6mediumRanked #6 in Factuality.
7OGPT-5.4
OpenAI		Not SOTA · #7mediumRanked #7 in Factuality.
8AClaude Fable 5
Anthropic		Not SOTA · #8mediumRanked #8 in Factuality.
9GGemini 3 Pro
Google DeepMind		Not SOTA · #9mediumRanked #9 in Factuality.
Evidence recipe

What can move this crown