SO-Arena v1.0 - Reliability: leaderboard
SO-Arena v1.0 native reliability. Stability measures consistency under option reordering, null discrimination measures missing-answer handling, and reliability combines the two. The published JSON supplies these exact values; StartLux null scores are derived from rounded reliability values. Native model inference paths and API interfaces remain separate. Metric: Native reliability (%). Higher is better.
Metric: Native reliability (%). Source: raw.githubusercontent.com. Saturation forecast: Rough model projection: around 2026. 19 models tracked. Updated 14 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | JevAny-27B | 84.11 | ||
| 2 | Jev 1.14.0 | 83.45 | ||
| 3 | Sieve-31B-v3 | 81.31 | ||
| 4 | KnowLine-31B-Gen1 | 81.01 | ||
| 5 | Kev 27B | 80.78 | ||
| 6 | StartLux-v1.1-4B-AutoThink | 80.5 | ||
| 7 | StartLux-v1.1-4B-Instant | 78.9 | ||
| 8 | GLiDE v1.2 | 77.57 | ||
| 9 | PPLX-Decider-v1.2 | 75.29 | ||
| 10 | Clef 27B | 73.21 | ||
| 11 | Clef flash 9.5B | 71 | ||
| 12 | JevAny-4B | 70.54 | ||
| 13 | PPLX-Decider-Flash-v1.2 | 67.92 | ||
| 14 | GPT-6 Luna | SO-Arena run: Decisions API; model=gpt-6-luna | 61.05 | #99 |
| 15 | H2O-Lightning-4B | 60.91 |
Interactive version: theaggregate.ai/benchmark?slug=so-arena-v1-0-reliability · How It Works · Data refreshed daily, snapshot 2026-11-16.