Coding AI Model Rankings
| # | Model | Coding | Cost |
|---|---|---|---|
| 1 |  Claude Opus 4.8 Anthropic | 88.6 | $10.00/M |
| 2 | Claude Opus 4.7 Anthropic | 83.5 | $10.00/M |
| 3 |  Gemini 3.1 Pro Google | 80.6 | $4.50/M |
| 4 |  GPT 5.5 OpenAI | 80.6 | $11.25/M |
| 5 | Gemini 3.5 Flash Google | 79.3 | $3.38/M |
| 6 | Claude Opus 4.6 Anthropic | 78.7 | $10.00/M |
| 7 |  GLM 5.2 Zhipu AI | 78.7 | $1.19/M |
| 8 |  DeepSeek V4 Pro DeepSeek | 77.6 | $0.54/M |
| 9 |  InklingNew Thinking Machines Lab | 77.6 | $1.76/M |
| 10 |  Qwen3.7 Max Qwen | 77.3 | $2.21/M |
| 11 | GPT 5.4 OpenAI | 76.9 | $5.63/M |
| 12 | Kimi K2.6 MoonshotAI | 76.7 | $1.37/M |
| 12 | Claude Opus 4.5 Anthropic | 76.7 | $10.00/M |
| 13 | Gemini 3 Flash Google | 75.4 | $1.13/M |
| 14 | Claude Sonnet 4.6 Anthropic | 75.2 | $6.00/M |
| 15 | GPT 5.3 Codex OpenAI | 74.8 | $4.81/M |
| 16 | GLM 5.1 Zhipu AI | 74.2 | $1.48/M |
| 17 | Kimi K2.5 MoonshotAI | 73.8 | $1.14/M |
| 17 | GPT 5.2 OpenAI | 73.8 | $4.81/M |
| 18 | GPT 5 OpenAI | 73.6 | $3.44/M |
| 19 | Claude Opus 4.1 Anthropic | 73.3 | $30.00/M |
| 20 | Gemini 3 Pro Google | 72.9 | — |
| 21 | GLM 5 Zhipu AI | 72.1 | $1.35/M |
| 22 | Claude Sonnet 4.5 Anthropic | 71.3 | $6.00/M |
| 23 |  Grok Build 0.1 xAI | 70.8 | $1.25/M |
| 24 | Claude Opus 4 Anthropic | 70.7 | $30.00/M |
| 25 | GPT 5.1 OpenAI | 68.0 | $3.44/M |
| 26 | GPT 5 Mini OpenAI | 64.7 | $0.69/M |
| 27 | o3 OpenAI | 62.3 | $3.50/M |
| 28 | Qwen3.6 Plus Qwen | 57.9 | $0.73/M |
| 29 | Gemini 2.5 Pro Google | 57.6 | $3.44/M |
| 30 | GPT 4.1 OpenAI | 48.5 | $3.50/M |
| 31 | GPT 4o OpenAI | 31.0 | $4.38/M |
33 of 33 models, ranked by SWE-bench Verified