Long-Context Reasoning benchmark
380 AI models ranked on Long-Context Reasoning. Each row shows the model’s score next to its cheapest API price per 1M tokens where it has one, so you can weigh quality against cost.
Top model today
Kimi K3 (Moonshot) leads at 89%, from $0.70 per 1M input OpenRouter routed quote.
Data via Artificial Analysis AA-LCR →Models ranked
380
on this benchmark
Top score
89%
current leader
Type
Composite
index
Updated
Oct 14, 2026
benchmark scores
Cost vs Long-Context Reasoning
245 priced modelsEach labelled name links to that model’s page. Curated to the cost-efficiency frontier, top scorers and cheapest so labels stay readable; the full field is in the leaderboard table below (and via “select all”). Reasoning models (extended “thinking” before answering) carry a ring around the dot.
Models ranked on Long-Context Reasoning
highest score first · 380 models| # | ||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Kimi K3 |  Moonshot | 89% | $0.70 Routed quote | $12.50 via Sail | |||||||||||||||||||||||||||||
| 2 | Step 5 Preview | Stepfun | 88% | n/a | n/a | |||||||||||||||||||||||||||||
| 3 | MiMo-V2.6-Pro |  Xiaomi | 86% | $0.435 via Xiaomi Mimo | $0.87 via Xiaomi Mimo | |||||||||||||||||||||||||||||
| 4 | Claude Fable 5.1 |  Anthropic | 85% | $10.00 via Anthropic | $50.00 via Anthropic | |||||||||||||||||||||||||||||
| 5 | Claude Opus 5.5 | Anthropic | 85% | $4.00 via Anthropic | $20.00 via Databricks | |||||||||||||||||||||||||||||
| 6 | GPT-5.5 |  OpenAI | 84% | $5.00 via OpenAI | $30.00 via OpenAI | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 7 | DeepSeek V4.1 Flash |  DeepSeek | 84% | $0.01 via Coralbricks | $0.60 via Sail | |||||||||||||||||||||||||||||
| 8 | GPT-5.6 Sol | OpenAI | 84% | $2.00 Routed quote | $10.00 Routed quote | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 9 | GPT-5.6 Luna | OpenAI | 84% | $0.20 via OpenAI | $1.20 via OpenAI | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 10 | GPT-6 Sol | OpenAI | 84% | $2.00 via OpenAI | $10.00 via OpenAI | |||||||||||||||||||||||||||||
| 11 | Muse Wonder Full (Max) |  Meta | 84% | n/a | n/a | |||||||||||||||||||||||||||||
| 12 | GPT-6 Luna | OpenAI | 83% | $0.10 via OpenAI | $0.50 via OpenAI | |||||||||||||||||||||||||||||
| 13 | GPT-5.3-Codex | OpenAI | 83% | $1.75 via Aihubmix | $14.00 via Aihubmix | |||||||||||||||||||||||||||||
| 14 | Solar Mini 4 | Other | 83% | $0.05 Routed quote | $0.20 Routed quote | |||||||||||||||||||||||||||||
| 15 | Muse Glimmer | Meta | 83% | n/a | n/a | |||||||||||||||||||||||||||||
| 16 | MiniMax M3 |  MiniMax | 83% | $0.23 via Wandb | $0.96 via Wandb | |||||||||||||||||||||||||||||
| 17 | GPT-5.6 Terra | OpenAI | 83% | $2.00 via OpenAI | $12.00 via OpenAI | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 18 | GPT-6.1 Sol | OpenAI | 83% | $2.00 via OpenAI | $10.00 via OpenAI | |||||||||||||||||||||||||||||
| 19 | Muse Spark 1.3 | Other | 83% | $1.25 via Azure | $4.25 via Azure | |||||||||||||||||||||||||||||
| 20 | Ling 3.1 Flash | InclusionAI | 83% | n/a | n/a | |||||||||||||||||||||||||||||
| 21 | Agnes 2.5 Pro Beta | Sapiens-ai | 83% | n/a | n/a | |||||||||||||||||||||||||||||
| 22 | Claude Haiku 5.5 | Anthropic | 83% | $0.10 via Anthropic | $0.50 via Anthropic | |||||||||||||||||||||||||||||
| 23 | GPT-5.2 | OpenAI | 83% | $1.75 via OpenAI | $14.00 via OpenAI | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 24 | Claude Sonnet 5.5 | Anthropic | 83% | $2.00 via Anthropic | $10.00 via Anthropic | |||||||||||||||||||||||||||||
| 25 | Claude Fable 5 | Anthropic | 82% | $10.00 via Anthropic | $50.00 via Anthropic | |||||||||||||||||||||||||||||
| 26 | GPT-5.2-Codex | OpenAI | 82% | $1.75 via Databricks | $14.00 via Databricks | |||||||||||||||||||||||||||||
| 27 | Claude Sonnet 5 | Anthropic | 82% | $2.00 via Anthropic | $10.00 via Anthropic | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 28 | Qwen3.8 27B |  Alibaba | 82% | $0.04 Routed quote | $1.49 via Cerebras | |||||||||||||||||||||||||||||
| 29 | Gemini 3.1 Pro Preview |  Google | 82% | $2.00 via Google | $12.00 via Google | |||||||||||||||||||||||||||||
| 30 | GPT-5.4 | OpenAI | 82% | $2.50 via Databricks | $15.00 via OpenAI | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 31 | Gemini 3.7 Flash | Google | 82% | $0.75 via Google | $3.75 via Google | |||||||||||||||||||||||||||||
| 32 | Nex-N2-Pro | Other | 82% | $0.25 Routed quote | $1.00 Routed quote | |||||||||||||||||||||||||||||
| 33 | Gemini 3.8 Flash | Google | 81% | $0.75 via Google | $3.75 via Google | |||||||||||||||||||||||||||||
| 34 | Mistral Large 4 |  Mistral | 81% | $0.68 via Mistral | $2.09 via Mistral | |||||||||||||||||||||||||||||
| 35 | DeepSeek V4 Flash Vision (Reasoning, Max Effort) | DeepSeek | 81% | n/a | n/a | |||||||||||||||||||||||||||||
| 36 | Kimi K2.6 | Moonshot | 81% | $0.65 via Wandb | $3.40 via Novita | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 37 | GPT-6 Astra | OpenAI | 81% | $10.00 via OpenAI | $50.00 via OpenAI | |||||||||||||||||||||||||||||
| 38 | Muse Wonder | Other | 81% | $4.00 Routed quote | $20.00 Routed quote | |||||||||||||||||||||||||||||
| 39 | Qwen3.6 Max Preview | Alibaba | 81% | n/a | n/a | |||||||||||||||||||||||||||||
| 40 | DeepSeek V4 Pro 0813 | DeepSeek | 80% | $0.66 Routed quote | $1.98 Routed quote | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 41 | Grok 4.6 |  xAI | 80% | $2.00 via xAI | $6.00 via xAI | |||||||||||||||||||||||||||||
| 42 | Qwen3.8 2.4T A95B | Alibaba | 80% | $2.00 via Aihubmix | $6.00 via Aihubmix | |||||||||||||||||||||||||||||
| 43 | Qwen3.8 Max (0902) | Alibaba | 80% | $2.00 Routed quote | $6.00 Routed quote | |||||||||||||||||||||||||||||
| 44 | GLM 5.3 Flash |  Zhipu | 80% | $0.11 via Sail | $0.35 via Sail | |||||||||||||||||||||||||||||
| 45 | Claude Sonnet 4.6 | Anthropic | 80%reasoning: adaptive | $3.00 via Databricks | $15.00 via Anthropic | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 46 | Gemini 3.6 Flash | Google | 80% | $0.75 via Google | $3.75 via Google | |||||||||||||||||||||||||||||
| 47 | GPT-5.1 | OpenAI | 80% | $1.25 via Databricks | $10.00 via Databricks | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 48 | K2 Horizon 375B A23B | Mbzuai-institute-of-foundation-models | 80% | n/a | n/a | |||||||||||||||||||||||||||||
| 49 | DeepSeek V4 Flash 0731 | DeepSeek | 80% | $0.016 Routed quote | $0.153 Routed quote | |||||||||||||||||||||||||||||
| 50 | GLM 5.3 | Zhipu | 80% | $0.079 Routed quote | $3.08 via Sail | |||||||||||||||||||||||||||||
Frequently asked questions
What is the Long-Context Reasoning benchmark?
Measures a model’s ability to retrieve, synthesise and reason across very long inputs spanning tens to hundreds of thousands of tokens, beyond simple fact lookup. Artificial Analysis reports this as AA-LCR; the broader category also draws on evaluations such as RULER and LongBench.
Which AI model scores highest on Long-Context Reasoning?
Kimi K3 (Moonshot) leads with 89%, from $0.70 per 1M input tokens as an OpenRouter routed quote, while Moonshot lists it at $3.00 per 1M input.
How many models are ranked on Long-Context Reasoning?
380 models carry a Long-Context Reasoning score. Scores come from Artificial Analysis; where a model has a listed API price it is drawn from LiteLLM and OpenRouter, and models with no current price are listed without one.
Other benchmarks
compare the same models on a different evalEvery weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI