SO-Arena v1.0 - Retrieval & Reranking: leaderboard
SO-Arena v1.0 Retrieval & Reranking 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
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | KnowLine-31B-Gen1 | 64 | ||
| 2 | Jeva-4B | 64 | ||
| 3 | Sieve-31B-v3 | 63.5 | ||
| 4 | GPT-6 Sol | Medium | 62.5 | #26 |
| 5 | GPT-6 Luna | Medium | 62 | #99 |
| 6 | Clef 27B | 61 | ||
| 7 | H2O-Lightning-4B | 61 | ||
| 8 | Jev 1.14.0 | 59.5 | ||
| 9 | Kev 27B | 59 | ||
| 10 | Clef flash 9.5B | 57.5 | ||
| 11 | JevAny-27B | 57 | ||
| 12 | GLiDE v1.2 | 57 | ||
| 13 | PPLX-Decider-Flash-v1.2 | 56 | ||
| 14 | PPLX-Decider-v1.2 | 56 | ||
| 15 | StartLux-v1.1-4B-AutoThink | 56 |
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-retrieval-reranking · How It Works · Data refreshed daily, snapshot 2026-11-16.