Best Long Context Coding Models
Long-context models are valuable for agent workflows that need large repositories, logs, documentation, and multi-file reasoning.
| # | Model | DeepSWE | Context | Cost | Open |
|---|---|---|---|---|---|
| 1 | Muse Wonder Full Meta | 79.0 | 1M | not listed | No |
| 2 | Muse Wonder Meta | 78.8 | 1M | $4/$20 | No |
| 3 | Gemini 4 Argon Google | 77.9 | 1M | not listed | No |
| 4 | Muse Spark 1.3 Meta | 75.4 | 1M | $1.25/$4.25 | No |
| 5 | GPT-6.1 Sol OpenAI | 75.2 | 1.1M | $2/$10 | No |
| 6 | Ember-1 Fireworks AI | 75.2 | 1M | $3/$15 | No |
| 7 | Claude Opus 5.5 Anthropic | 74.2 | 1M | $4/$20 | No |
| 8 | GPT-6 Astra OpenAI | 74.1 | 272K+ | $10/$50 | No |
| 9 | Gemini 3.8 Flash Google | 73.7 | 1M | $0.75/$3.75 | No |
| 10 | GPT-5.6 Sol OpenAI | 73.0 | 1.1M | $5/$30 | No |
| 11 | MiMo-V2.6-Pro Xiaomi | 71.9 | 1M | $0.435/$0.87 | Yes |
| 12 | Grok 4.7 xAI | 71.0 | 500K | $2/$6 | No |
| 13 | Claude Sonnet 5.5 Anthropic | 71.0 | 1M | $2/$10 | No |
| 14 | GPT-5.6 Terra OpenAI | 70.0 | 1.1M | $2.50/$15 | No |
| 15 | Claude Fable 5 Anthropic | 70.0 | 1M | $10/$50 | No |
| 16 | Kimi K3 Moonshot AI | 69.0 | 1M | $3/$15 | Yes |
| 17 | GPT-6 Sol OpenAI | 68.8 | 1.1M | $2/$10 | No |
| 18 | Claude Opus 5 Anthropic | 68.8 | 1M | $5/$25 | No |
| 19 | MiMo-V2.6-Flash Xiaomi | 67.9 | 1M | $0.14/$0.28 | Yes |
| 20 | GPT-5.6 Luna OpenAI | 67.0 | 1.1M | $1/$6 | No |
| 21 | GPT-5.5 OpenAI | 67.0 | 258K | $6/$25 | No |
| 22 | GPT-6 Luna OpenAI | 66.6 | 1.1M | $0.10/$0.50 | No |
| 23 | DeepSeek V4 Pro 0813 DeepSeek | 62.8 | 1M | $0.435/$0.87 | Yes |
| 24 | Mistral Large 4 Mistral AI | 61.7 | 1M | $0.68/$2.09 | No |
| 25 | Muse Spark 1.2 Meta | 59.3 | 1M | $1.25/$4.25 | No |
| 26 | Claude Opus 4.8 Anthropic | 59.0 | 1M | $5/$25 | No |
| 27 | Qwen3.8 Max Alibaba | 56.6 | 1M | $2/$6 | Yes |
| 28 | Claude Sonnet 5 Anthropic | 54.0 | 1M | not listed | No |
| 29 | Grok 4.5 xAI | 54.0 | 500K | $2/$6 | No |
| 30 | Muse Spark 1.1 Meta | 53.0 | 1M | $1.25/$4.25 | No |
| 31 | GPT-5.4 OpenAI | 52.0 | 1M | $5/$20 | No |
| 32 | GLM-5.2 Z.ai | 44.0 | 1M | $0.95/$3 | Yes |
| 33 | Qwen3.8-27B Alibaba | 42.2 | 262K | not listed | Yes |
| 34 | Laguna S 2.1 Poolside | 40.4 | 1M | not listed | Yes |
| 35 | Claude Sonnet 4.6 Anthropic | 30.0 | 1M | not listed | No |
| 36 | Gemini 3.1 Pro Google | 12.0 | 1M+ | not listed | No |
How to read this: Agent pages score the wrapper and workflow. Stack pages score agent plus model combinations.
Related rankings
Other useful paths through the dataset.
Best CLI AI Coding Agents
Terminal-first coding agents are best when you want repo-level edits, scriptable workflows, and less IDE lock-in.
36 entries
Best Open Source AI Coding Agents
Open-source agents are strongest when you want provider choice, local-model support, and transparent agent behavior.
36 entries
Best AI Coding Agents for VS Code
IDE-focused agents are best for daily coding, codebase navigation, completions, and fast multi-file edits.
36 entries
Best Browser AI Coding Agents
Browser coding agents are useful when you want to build, preview, and ship without managing a local development environment.
36 entries