WeightBench - Macro SWB (42 tasks): leaderboard
Default difficulty, seed0. Claude2samples/task; DeepSeek/GPT1sample/task. Quarantined/invalid submissions score0 (unreviewed lower bounds). Task scores average across runs then tasks; macro averages5tracks. GPT excludes4 loop Fix tasks; use common38task macro, never pool GPT9taskFix with13taskFix. Metric: Native S_WB (0–1). Source: https://arxiv.org/html/2611.18553v1
Metric: Native S_WB (0–1). Source: arxiv.org. Saturation forecast: Around September 2027. 4 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 | 0.535 | #7 |
| 2 | Claude Sonnet 5.5 | 0.466 | #21 |
| 3 | Claude Haiku 5.5 | 0.402 | #76 |
| 4 | DeepSeek V4 Flash | 0.215 | #265 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=weightbench-macro-swb-42-tasks · How It Works · Data refreshed daily, snapshot 2026-11-17.