AA-LCR — leaderboard
AA-LCR evaluates model capability on long context tasks from the linked upstream source with Score as the primary reported metric.
Metric: Score (self-reported). Source: benchmarklist.com. Status: saturated. 331 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 Codex | 75.7 |
| 2 | GPT-5 | 75.6 |
| 3 | GPT-5.1 | 75 |
| 4 | GPT-5.5 | 74.3 |
| 5 | GPT-5.4 | 74 |
| 6 | Claude Opus 4.5 | 74 |
| 7 | GPT-5.3 Codex | 74 |
| 8 | KAT-Coder-Pro V1 | 74 |
| 9 | MiMo-V2.5-Pro | 73.3 |
| 10 | Gemini 3.1 Pro (Preview) | 72.7 |
| 11 | GPT-5.2 | 72.7 |
| 12 | Gemini 3.5 Flash (Medium) | 71 |
| 13 | Claude Opus 4.6 (Max) | 70.7 |
| 14 | Claude Sonnet 4.6 (Max) | 70.7 |
| 15 | Claude Haiku 4.5 | 70.3 |
Interactive version: theaggregate.ai/benchmark?slug=aa-lcr · How the rankings work · Data refreshed daily, snapshot 2026-07-22.