Benchmarks · long-context
AA-LCR v1.1
AA-LCR: long-context reasoning over ~100k-token document sets; pass rate.
137 models · 266 results · data as of 2026-10-29 · artificialanalysis.ai ↗
Leaderboard
Kimi K3 max
More from this benchmark
3 published measuresScore vs any published measure3 measures: sub-scores, splits, counts
Breakdown
darker is better within each column · click a column to sort| Model | |||
|---|---|---|---|
| Kimi K3 max | 9,521,736 | 11,024 | 141,845 |
| MiMo V2.6 Pro | 10,457,619 | 43,985 | 173,118 |
| Fable 5.1 max, fallback | 14,353,607 | 51,271 | 252,368 |
| Opus 5.5 max, fallback | 14,353,608 | 51,510 | 460,538 |
| GPT-5.5 high | 9,433,972 | 12,209 | 108,200 |
| DeepSeek V4.1 Flash max | 9,542,844 | 7,858 | 301,839 |
| Gemini 3.8 Flash medium | 10,719,200 | 22,650 | 225,297 |
| GPT-5.6 Sol max | 9,433,272 | 7,487 | 113,921 |
| GPT-6.1 Sol low | 9,433,272 | 8,221 | 4,401 |
| GPT-5.6 Luna max | 9,433,588 | 8,078 | 162,899 |
| GPT-6 Sol high | 9,433,272 | 5,183 | 21,667 |
| GPT-5.3 Codex xhigh | 9,433,672 | 8,200 | 178,004 |
| GPT-6 Luna max | 9,433,272 | 6,572 | 144,280 |
| Gemini 3.7 Flash medium | 10,719,200 | 19,010 | 119,689 |
| GPT-5.6 Terra max | 9,433,272 | 8,801 | 193,711 |
| Ling 3.1 Flash | 10,987,846 | 29,337 | 140,260 |
| MiniMax M3 | 9,354,816 | 16,043 | 124,859 |
| Muse Spark 1.3 max | 9,378,348 | 15,885 | 353,552 |
| Haiku 5.5 max | 14,353,608 | 27,002 | 964,878 |
| Sonnet 5.5 max, fallback | 14,353,608 | 37,767 | 484,520 |
| DeepSeek V4.1 Flash 1017 max | 9,542,844 | 9,179 | 322,493 |
| GPT-5.2 xhigh | 9,433,672 | 9,021 | 301,948 |
| GPT-6.1 Terra max | 9,433,272 | 7,567 | 156,892 |
| GPT-5.2 Codex xhigh | 9,433,672 | 8,047 | 637,077 |
| Opus 5 medium | 14,353,408 | 41,683 | 38,641 |
All results
266 rows| # | Model | Effort | AA-LCR v1.1 |
|---|---|---|---|
| 1 | Kimi K3 | max | 88.7% |
| 2 | MiMo V2.6 Pro | 86.3% | |
| 3 | Fable 5.1 | max | 85.3% |
| 4 | Fable 5.1 | medium | 84.7% |
| 5 | Opus 5.5 | max | 84.7% |
| 6 | Opus 5.5 | xhigh | 84.7% |
| 7 | Opus 5.5 | medium | 84.3% |
| 8 | GPT-5.5 | high | 84.3% |
| 9 | GPT-5.5 | xhigh | 84.3% |
| 10 | DeepSeek V4.1 Flash | max | 84.0% |
| 11 | Gemini 3.8 Flash | medium | 84.0% |
| 12 | GPT-5.6 Sol | max | 84.0% |
| 13 | GPT-6.1 Sol | low | 84.0% |
| 14 | Fable 5.1 | high | 83.7% |
| 15 | GPT-5.6 Luna | max | 83.7% |
| 16 | GPT-6 Sol | high | 83.7% |
| 17 | GPT-6 Sol | max | 83.7% |
| 18 | GPT-5.3 Codex | xhigh | 83.3% |
| 19 | GPT-6 Luna | max | 83.3% |
| 20 | GPT-6.1 Sol | medium | 83.3% |
| 21 | Fable 5.1 | xhigh | 83.0% |
| 22 | Gemini 3.7 Flash | medium | 83.0% |
| 23 | GPT-5.5 | medium | 83.0% |
| 24 | GPT-5.6 Terra | max | 83.0% |
| 25 | GPT-6.1 Sol | max | 83.0% |
| 26 | Ling 3.1 Flash | 83.0% | |
| 27 | MiniMax M3 | 83.0% | |
| 28 | Muse Spark 1.3 | max | 83.0% |
| 29 | Muse Spark 1.3 | xhigh | 83.0% |
| 30 | Haiku 5.5 | max | 82.7% |