SO-Arena v1.0 - Knowledge & Commonsense: leaderboard

SO-Arena v1.0 Knowledge & Commonsense domain score on the source-selected1232-task panel. Domain scores average native task credits for static decisions, tool outcomes or web progress, then scale to0–100. The full release has2919tasks; this leaderboard emphasizes the highest difficulty tiers and keeps all untiered sentiment/knowledge tasks. Metric: Native panel task credit mean (%). Higher is better.

Metric: Native panel task credit mean (%). Source: huggingface.co. Saturation forecast: Around February 2027. 20 models tracked. Updated 14 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Clef flash 9.5B95.5
2PPLX-Decider-v1.295
3GLiDE v1.295
4Clef 27B94.5
5JevAny-27B94.5
6GPT-6 SolMedium94#26
7KnowLine-31B-Gen193
8Sieve-31B-v393
9Jev 1.14.092.5
10Kev 27B92
11PPLX-Decider-Flash-v1.291
12H2O-Lightning-4B91
13GPT-6 LunaMedium90#99
14JevAny-4B89.5
15StartLux-v1.1-4B-Instant88.5

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.

Interactive version: theaggregate.ai/benchmark?slug=so-arena-v1-0-knowledge-commonsense · How It Works · Data refreshed daily, snapshot 2026-11-16.