TasteVal - Performance Multiplier: leaderboard
The final-result companion to the TasteVal compute multiplier (P-Zero Research, 2026), on the same eight withheld AI R&D tasks and Researcher and coding-agent protocol. Each run scores the test result of its official submission after the full 40 GPU-hour budget, rescaled per task so the naive baseline is 0 and the best human expert attempt is 1, whatever compute it used; seeds are averaged and tasks combined geometrically. Higher is better, with no upper limit.
Metric: Performance multiplier against the expert baseline: test score of the official submission of each run within the 40 H100-hour budget, rescaled per task so the naive baseline is 0 and the best human expert attempt is 1 (runs below the naive baseline count 0), arithmetic mean over seeds and then geometric mean over the 8 withheld AI R&D tasks (a task with no run above the naive baseline enters at 0.01), regardless of compute used; same Researcher and fixed Coder protocol as the compute multiplier; from 0 with no upper limit; higher is better. Source: arxiv.org. Saturation forecast: Around August 2027. 22 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 | Max | 1.14 | #9 |
| 2 | GPT-6 Astra | Max | 1.13 | #10 |
| 3 | Claude Opus 5 | Max | 1.11 | #26 |
| 4 | Claude Fable 5.1 | Max | 1.09 | #20 |
| 5 | Claude Opus 4.8 | Max | 1.01 | #65 |
| 6 | GPT-5.6 Sol | Max | 0.92 | #37 |
| 7 | GLM-5.3 | Max | 0.89 | #72 |
| 8 | Kimi K3 | Thinking | 0.89 | #61 |
| 9 | GPT-5.5 | xHigh | 0.84 | #54 |
| 10 | Claude Opus 4.6 | Max | 0.78 | #113 |
| 11 | Claude Opus 4.7 | Max | 0.75 | #85 |
| 12 | GPT-5.2 | High | 0.7 | #185 |
| 13 | GPT-5.4 | xHigh | 0.6 | #135 |
| 14 | GPT-5 | High | 0.53 | #178 |
| 15 | O3 | High | 0.43 | #237 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=tasteval-performance-multiplier · How It Works · Data refreshed daily, snapshot 2026-11-21.