Coding models, ranked
Writing code is not a one-shot prompt. A model needs room for several files at once, tool calling to reach your build and your tests, and structured output so a patch comes back as a patch. Everything below has all three and fits at least 64k tokens of context.
Most used in this category
Each model's share of this category's usage over the last 30 days, and its output price per 1M tokens in toman.
- 1
Gemini 3.8 Flash50% share1,298,323 toman - 2Gemini 2.5 Flash Lite29% share138,488 toman
- 3Gemini 3.1 Flash Lite5.6% share519,329 toman
- 4Claude Sonnet 54.6% share3,462,194 toman
- 5Gemini 2.5 Flash4.1% share865,548 toman
Best value in this category
Score out of 100: 50% cheapness, 30% capabilities, 20% context size — not a quality benchmark.
| # | Model | Context (tokens) | ≈ 1,000 words (toman) | Score |
|---|---|---|---|---|
| 1 | 1GLM Flash Latest | 1,048,576 | 54 | 87.7 |
| 2 | 2Qwen3.7 Flash | 1,000,000 | 72 | 84.4 |
| 3 | 3GPT-6 Luna Pro (batch) | 1,050,000 | 135 | 83.8 |
| 4 | 4GPT-6 Luna (batch) | 1,050,000 | 135 | 83.8 |
| 5 | 5Claude Haiku 5.5 (batch) | 1,000,000 | 135 | 83.6 |
| 6 | 6GPT-5 Nano (batch) | 400,000 | 101 | 83.6 |
| 7 | 7Ling 3.0 Tiny | 262,144 | 27 | 82.4 |
| 8 | 8Ling 3.0 Flash | 262,144 | 38 | 80.7 |
| 9 | 9GLM 5.3 Flash (batch) | 1,048,576 | 104 | 80.6 |
| 10 | 10Gemma 4 26B A4B | 262,144 | 67 | 80.6 |
| 11 | 11Gemini 2.5 Flash Lite | 1,048,576 | 225 | 78.2 |
| 12 | 12Qwen3.5-Flash | 1,000,000 | 146 | 76.8 |
| 13 | 13Ternary Bonsai 2 9B | 262,144 | 95 | 76.8 |
| 14 | 14GPT-6 Luna | 1,050,000 | 270 | 76.3 |
| 15 | 15GPT-6 Luna Pro | 1,050,000 | 270 | 76.3 |
Full list of models that hold up in a real codebase with prices →