SO-Arena v1.0 - Text-based Web Interaction: leaderboard
SO-Arena v1.0 Text-based Web Interaction 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 May 2027. 20 models tracked. Updated 14 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-6 Sol | Medium | 53.22 | #26 |
| 2 | PPLX-Decider-v1.2 | 50.24 | ||
| 3 | GLiDE v1.2 | 48.96 | ||
| 4 | GPT-6 Luna | Medium | 47.5 | #99 |
| 5 | Kev 27B | 45.43 | ||
| 6 | KnowLine-31B-Gen1 | 44.03 | ||
| 7 | Sieve-31B-v3 | 42.82 | ||
| 8 | Clef 27B | 42.57 | ||
| 9 | JevAny-27B | 41.3 | ||
| 10 | Jev 1.14.0 | 40.66 | ||
| 11 | PPLX-Decider-Flash-v1.2 | 33.65 | ||
| 12 | StartLux-v1.1-4B-Instant | 31.47 | ||
| 13 | StartLux-v1.1-4B-AutoThink | 30.61 | ||
| 14 | H2O-Lightning-4B | 28.25 | ||
| 15 | Clef flash 9.5B | 25.18 |
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-text-based-web-interaction · How It Works · Data refreshed daily, snapshot 2026-11-16.