Guesswork: leaderboard
This site's own live benchmark for predicting benchmark scores: frontier and budget LLMs forecast newly published (model, benchmark) results a day before they land, scored in per-benchmark z-units (MAE, lower is better) against the same-information statistical baseline The Aggregate.
Metric: MAE (z-score units). Source: theaggregate.ai. 33 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6.1 Sol | 0.59 | #7 |
| 2 | Claude Opus 5.5 | 0.61 | #3 |
| 3 | Claude Fable 5.1 | 0.62 | #9 |
| 4 | GPT-6 Astra | 0.62 | #6 |
| 5 | Claude Sonnet 5.5 | 0.63 | #11 |
| 6 | Gemini 3.7 Flash | 0.65 | #23 |
| 7 | GPT-5.6 Luna | 0.67 | #68 |
| 8 | Claude Opus 5 | 0.68 | #12 |
| 9 | GPT-5.6 Terra | 0.7 | #41 |
| 10 | GPT-5.5 | 0.71 | #31 |
| 11 | Grok 4.6 | 0.74 | #26 |
| 12 | Claude Opus 4.8 | 0.76 | #37 |
| 13 | GPT-5.1 | 0.85 | #135 |
| 14 | Mistral Large 3 | 0.91 | #401 |
| 15 | Grok 4.3 | 0.93 | #188 |
No result here: #8 Gemini 4 Argon, #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=guesswork · How It Works · Data refreshed daily, snapshot 2026-10-20.