WeightBench - Fix Non-Loop 9-Task Subset: leaderboard
GPT-6.1Sol9non-loop Fix tasks; separate from13task full-track population; seed0, 1sample/task; quarantined/invalid0. Metric: Native S_WB (0–1). Source: https://arxiv.org/html/2611.18553v1
Metric: Native S_WB (0–1). Source: arxiv.org. 1 model tracked. Updated 17 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6.1 Sol | 0.571 | #12 |
Interactive version: theaggregate.ai/benchmark?slug=weightbench-fix-non-loop-9-task-subset · How It Works · Data refreshed daily, snapshot 2026-11-17.