AA Long Context Reasoning — leaderboard

AA-LCR: ability to extract, reason about, and synthesize information from documents of 10k-100k tokens (100 questions). Proprietary AA benchmark.

Metric: Accuracy (%). Source: artificialanalysis.ai. Status: saturation imminent. 472 models tracked.

Top models

#ModelScore
1GPT-5.2 Codex (xHigh)75.67
2GPT-5 (High)75.6
3GPT-5.1 (High)75
4Kimi K374.67
5GPT-5.5 (xHigh)74.33
6MiniMax-M374
7GPT-5.4 (xHigh)74
8Claude Opus 4.5 (Thinking)74
9KAT-Coder-Pro V174
10GPT-5.6 Terra (Max)74
11GPT-5.6 Luna (Max)74
12GPT-5.3 Codex (xHigh)74
13GPT-5.6 Sol (Max)73.67
14MiMo-V2.5-Pro73.33
15GPT-5.5 (High)73.33

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