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

#ModelScore
1GPT-5.2 Codex75.7
2GPT-575.6
3GPT-5.175
4GPT-5.574.3
5GPT-5.474
6Claude Opus 4.574
7GPT-5.3 Codex74
8KAT-Coder-Pro V174
9MiMo-V2.5-Pro73.3
10Gemini 3.1 Pro (Preview)72.7
11GPT-5.272.7
12Gemini 3.5 Flash (Medium)71
13Claude Opus 4.6 (Max)70.7
14Claude Sonnet 4.6 (Max)70.7
15Claude Haiku 4.570.3

Interactive version: theaggregate.ai/benchmark?slug=aa-lcr · How the rankings work · Data refreshed daily, snapshot 2026-07-22.