AA-LCR
Long-context reasoning across ~100k-token document sets. Run by Artificial Analysis.
- Published by
- Artificial Analysis
- Category
- Long context
- Index weight
- 1.0
- Models
- 466
- Data as of
- 9 Sept 2026
Source: Artificial Analysis (artificialanalysis.ai). Data taken from the public leaderboard.
- 1Kimi K388.7%
- 2Claude Fable 5.185.3%
- 3Claude Fable 5.184.7%
- 4GPT-5.584.3%
- 5GPT-5.584.3%
- 6GPT-5.6 Sol84.0%
- 7Gemini 3.8 Flash84.0%
- 8Claude Fable 5.183.7%
- 9GPT-5.6 Luna83.7%
- 10GPT-5.3 Codex83.3%
- 11Muse Glimmer (high)83.3%
- 12Claude Fable 5.183.0%
- 13GPT-5.583.0%
- 14Gemini 3.7 Flash83.0%
- 15Muse Spark 1.383.0%
466 of 466
| # | |||||
|---|---|---|---|---|---|
| 1 | 88.7% | Kimi K3 (max) | 66.5 | – | |
| 2 | 85.3% | Claude Fable 5.1 (max with fallback) | 70.0 | – | |
| 3 | 84.7% | – | 68.0 | – | |
| 4 | 84.3% | GPT-5.5 (xhigh) | 66.6 | – | |
| 5 | 84.3% | – | 66.3 | – | |
| 6 | 84.0% | GPT-5.6 Sol (max) | 65.3 | – | |
| 7 | 84.0% | – | 63.5 | – | |
| 8 | 83.7% | – | 69.7 | – | |
| 9 | 83.7% | GPT-5.6 Luna (max) | 56.6 | – | |
| 10 | 83.3% | GPT-5.3 Codex (xhigh) | 62.4 | – | |
| 11 | 83.3% | – | 55.1 | – | |
| 12 | 83.0% | – | 70.3 | – | |
| 13 | 83.0% | – | 64.9 | – | |
| 14 | 83.0% | – | 64.4 | – | |
| 15 | 83.0% | – | 63.9 | – | |
| 16 | 83.0% | GPT-5.6 Terra (max) | 62.3 | – | |
| 17 | 83.0% | MiniMax-M3 | 56.9 | – | |
| 18 | Agnes 2.5 Pro BetaSapiens AI | 83.0% | – | – | – |
| 19 | 83.0% | Muse Spark 1.3 (max) | – | – | |
| 20 | 82.7% | GPT-5.2 (xhigh) | 61.5 | – | |
| 21 | 82.3% | Claude Fable 5 (with fallback) | 70.4 | – | |
| 22 | 82.3% | – | 67.5 | – | |
| 23 | 82.3% | – | 65.9 | – | |
| 24 | 82.3% | GPT-5.2 Codex (xhigh) | 60.7 | – | |
| 25 | 82.0% | – | 63.9 | – | |
| 26 | 82.0% | GPT-5.4 (xhigh) | 63.4 | – | |
| 27 | 82.0% | – | 63.1 | – | |
| 28 | 82.0% | Claude Sonnet 5 (max) | 61.2 | – | |
| 29 | 82.0% | Qwen3.8 27B (xhigh) | 57.1 | – | |
| 30 | 81.7% | – | 68.0 | – | |
| 31 | 81.7% | Gemini 3.7 Flash (high) | 61.7 | – | |
| 32 | 81.7% | – | 59.3 | – | |
| 33 | Nex-N2-ProNex AGIopen | 81.7% | – | – | – |
| 34 | 81.3% | Gemini 3.8 Flash (high) | 62.4 | – | |
| 35 | 81.3% | – | 61.7 | – | |
| 36 | 81.3% | DeepSeek V4 Flash Vision (max) | 57.4 | – | |
| 37 | 81.0% | – | 63.8 | – | |
| 38 | 81.0% | – | 62.3 | – | |
| 39 | 81.0% | – | 62.3 | – | |
| 40 | 81.0% | Kimi K2.6 | 60.6 | – | |
| 41 | 80.7% | GPT-6 Astra (max) | 69.9 | – | |
| 42 | 80.7% | – | 62.0 | – | |
| 43 | 80.7% | – | 61.9 | – | |
| 44 | 80.7% | – | 59.6 | – | |
| 45 | 80.3% | – | 66.3 | – | |
| 46 | 80.3% | – | 66.0 | – | |
| 47 | 80.3% | Grok 4.6 (high) | 63.6 | – | |
| 48 | 80.3% | DeepSeek V4 Pro 0813 (max) | 59.7 | – | |
| 49 | 80.3% | – | 58.1 | – | |
| 50 | 80.3% | – | – | – | |
| 51 | 80.0% | – | 69.5 | – | |
| 52 | 80.0% | – | 68.6 | – | |
| 53 | 80.0% | – | 65.8 | – | |
| 54 | 80.0% | – | 61.0 | – | |
| 55 | 80.0% | Gemini 3.6 Flash | 60.7 | – | |
| 56 | 80.0% | – | 60.3 | – | |
| 57 | 80.0% | GPT-5.1 (high) | 59.4 | – | |
| 58 | K2 Horizon 375B A23BMBZUAI Institute of Foundation Modelsopen | 80.0% | K2 Horizon 375B A23B | – | – |
| 59 | 79.7% | – | 67.4 | – | |
| 60 | 79.7% | – | 59.3 | – |