SPU Public Task-adjusted Mean: leaderboard
SPU Public Task-adjusted Mean — Public100tasks/private16tasks reported separately. Mainmeans exclude safetyrefusals and unrecoverableoutputs; schema-recoverable rankings included unchanged. ScoresareweightedSpearmancorrelation over experimentgroups, bounds[-1,1]. Task-adjusted mean is fitted additive task/configuration estimate and not guaranteed bounded, so do not infer [-1,1] bounds for adjusted estimate. Native per-row taskcoverage retained. No metric from APIcost/table3. Metric: Spearman correlation. Source: https://arxiv.org/html/2611.15049v1
Metric: Spearman correlation. Source: arxiv.org. Saturation forecast: Around April 2028. 12 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 | Max | 0.478 | #5 |
| 2 | GPT-6 Astra | Medium | 0.431 | #6 |
| 3 | Claude Opus 5 | Max | 0.424 | #20 |
| 4 | Claude Fable 5.1 | Max | 0.421 | #15 |
| 5 | Claude Sonnet 5.5 | Max | 0.393 | #19 |
| 6 | Doubao-Seed-Evolving-0909 | Max | 0.315 | |
| 7 | GPT-6.1 Sol | Max | 0.308 | #10 |
| 8 | Kimi K3.1 Pro | Max | 0.296 | #29 |
| 9 | DeepSeek V4.1 Flash | Max | 0.254 | #62 |
| 10 | Hy4 preview | Max | 0.245 | #71 |
| 11 | GLM-5.3 Flash | Max | 0.239 | #125 |
| 12 | Qwen 3.8 Max (0902) | Max | 0.227 | #49 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=spu-public-task-adjusted-mean · How It Works · Data refreshed daily, snapshot 2026-11-16.