Skip to content

Benchmark

Artificial Analysis LCR

Long context benchmarks measure how well models use information in long inputs. Scores are percentages. Higher is better.

Models measured
32
Scores recorded
41
Sources
2
IQ weight
1.94

Score distribution

64.7%
Mean
68.3%
Median
13.9%
Std dev
52%
10th percentile
77.7%
90th percentile
4.7%
Min
4.7%83.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.94 for chat models, measured over 28 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Solar Mini 4· LLM Stats data83.3%
2Muse Glimmer 30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim80%
3Muse Glimmer 30Bhigh reasoning· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.80%
4Beam 1.0 501B A23B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.2%
5Mercury 3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.7%
6Kimi K3max effort · temp 1.0 · top_p .95· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.74.7%
7GPT 5.4SenseNova 6.7 Flash-Lite official benchmark chart · chart setting· Reported by SenseTime / OpenSenseNova· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.74%
8Hy3 (Deep Infra)· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.4%
9Hy3 (Deep Infra)Hy3 official Benchmark Appendix · highest reasoning tier unless noted· Reported by Tencent Hunyuan· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.73.4%
10Mistral Smalllatest· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71.2%
11Solar Pro 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71%
12Claude Opus 4.6SenseNova 6.7 Flash-Lite official benchmark chart · chart setting· Reported by SenseTime / OpenSenseNova· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.70.7%
13Ling 3.0 Flash SanteLing-3.0-flash-Sante official evaluation image · highest reasoning tier · temperature 1.0 / top_p 0.95 unless otherwise stated · exact API snapshot and run count not published · Artificial Analysis long-context reasoning label · setting not further stated in card· Reported by Ant inclusionAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.70.5%
14Kimi K2.5setting not named by the source· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.70%
15Kimi K2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70%
16MiniMax M2.5official appendix· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.69.5%
17Qwen3 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim68.7%
18Qwen3.5 397B A17B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim68.7%
19Qwen3.5 397B A17BQwen3.5 release/model card · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.68.7%
20NVIDIA Nemotron 3.5 Super VL 120B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim68.6%
21Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim68.3%
22Qwen3.6 PlusQwen official release table · thinking mode unless benchmark requires otherwise· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.68.3%
23Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim66.9%
24Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim66.1%
25Nemotron 3 Ultra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim65.4%
26Nemotron 3 UltraNeMo Evaluator SDK · official table· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.65.4%
27Kimi K2.5SenseNova 6.7 Flash-Lite official benchmark chart · chart setting· Reported by SenseTime / OpenSenseNova· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.65.3%
28Ling 3.0 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim65.1%
29GLM 5SenseNova 6.7 Flash-Lite official benchmark chart · chart setting· Reported by SenseTime / OpenSenseNova· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.3%
30Qwen3.5 9B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim63%
31MiniMax M2.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62%
32Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58.5%
33Nemotron 3 Super 120B A12B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58.3%
34Nemotron 3 Super 120B A12BNeMo Evaluator / mostly NeMo Skills · published setting· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.58.3%
35Qwen3.5 4B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57%
36Qwen3.5 Omni PlusQwen3.5-Omni release · no-thinking setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57%
37Nemotron 3.5 Lightning 30B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim52%
38Nemotron 3.5 Lightning 30B A3Bofficial release table· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.52%
39Qwen3.5 Omni FlashQwen3.5-Omni release · no-thinking setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.46%
40Qwen3.5 2B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim25.6%
41Qwen3.5 0.8B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim4.7%

Data credits: Data by LLM Stats · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.