The Aggregate - Day-one Recall Check: leaderboard
Metric: Accuracy (%). Source: theaggregate.ai. Saturation forecast: Around June 2027. 33 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5 | 61.8 | #13 |
| 2 | Claude Opus 5 | 58.8 | #11 |
| 3 | Claude Fable 5.1 | 55.9 | #8 |
| 4 | GPT-5.5 | 47.1 | #26 |
| 5 | Claude Opus 4.8 | 41.2 | #33 |
| 6 | GPT-5.4 | 38.2 | #76 |
| 7 | GPT-5.2 | 38.2 | #105 |
| 8 | DeepSeek V4 Pro | 32.4 | #96 |
| 9 | Kimi K2.6 | 32.4 | #99 |
| 10 | Nemotron 3 Ultra | 32.3 | #234 |
| 11 | GPT-5.4 Mini | 29.4 | #202 |
| 12 | Qwen 3.6 35B A3B | 29.4 | #214 |
| 13 | Nemotron 3 Super | 26.5 | #327 |
| 14 | Qwen 3.6 Plus | 23.5 | #113 |
| 15 | Kimi K2 0905 | 23.5 | #282 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #9 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=the-aggregate-day-one-recall-check · How It Works · Data refreshed daily, snapshot 2026-10-11.