Tool Check
Best AI for coding
All tasks
Coding
Which model is best at coding?
Our pickClaude Opus 5.5Anthropic · $4 in · $20 outThe best model anyone can use, with enough evidence. When several tie, the cheapest of them.
Best you can downloadDeepSeek V4.1 FlashDeepSeek · $0.30 in · $1.20 out · downloadOpen weights: you can run it on your own computers.
Cheaper choiceClaude Sonnet 5.5Anthropic · $2 in · $10 outIn the top five, about 50% cheaper than our pick.
| Place | Model | Score | Price |
|---|---|---|---|
| 1 | Claude Opus 5.5Anthropic | 100.0 | $4 in · $20 out |
| 2 | Claude Sonnet 5.5Anthropic | 95.0 | $2 in · $10 out |
| 3 | Claude Fable 5.1Anthropic | 94.2 | $10 in · $50 out |
| 4 | GPT-6.1 SolOpenAI | 88.4 | $2 in · $10 out |
| 5 | GPT-6 AstraOpenAI | 88.0 | $10 in · $50 out |
| 6 | Claude Opus 5Anthropic | 87.6 | $5 in · $25 out |
| 7 | Claude Fable 5Anthropic | 87.0 | $10 in · $50 out |
| 8 | DeepSeek V4.1 FlashDeepSeek · download | 86.8 | $0.30 in · $1.20 out |
| 9 | Muse Spark 1.3Meta | 85.0 | No public API price |
| 10 | Kimi K3Moonshot AI (Kimi) · download | 84.4 | No public API price |
Models with overlapping uncertainty share a place (shown as “=”). Prices are US dollars per million tokens from each company’s own price page.
Ranked by our Silicon score, from 4 tests by 3 publishers.