Best coding models in 2026
The strongest coding models in the index, ranked by the average of SWE-bench Verified, HumanEval, LiveCodeBench.
What the data shows
GPT-5.2 Pro leads the coding group with an average of 87.7 across the selected benchmarks. The median for the group is 67.9.
Prices for the top 10 range from $19.42 to $21.39 per million input tokens.
How to read the ranking
- Check the individual benchmark scores, not just the composite.
- Test on your own examples; benchmark tasks differ from production tasks.
- Compare price and latency for the top candidates.
- Keep a fallback model for outages.
Best coding models
| # | Model | Provider | Input / 1M | Output / 1M | Context | Avg score |
|---|---|---|---|---|---|---|
| 1 | GPT-5.2 Pro | OpenAI | $21.32 | $76.33 | 2,000,000 | 89.6 |
| 2 | GPT-5.2 Max | OpenAI | $21.39 | $90.69 | 1,000,000 | 89.2 |
| 3 | Claude Opus 4.5 Pro | Anthropic | $20.98 | $85.59 | 200,000 | 89.1 |
| 4 | Grok 4 Reasoning | xAI | $19.67 | $93.29 | 2,000,000 | 87.8 |
| 5 | Claude Opus 4.5 | Anthropic | $19.42 | $75.27 | 400,000 | 87.7 |
| 6 | Claude Sonnet 4.5 Max | Anthropic | $19.90 | $95.47 | 1,000,000 | 87.2 |
| 7 | GPT-5.2 Reasoning | OpenAI | $20.98 | $102.78 | 1,000,000 | 87.5 |
| 8 | Claude Sonnet 4.5 Reasoning | Anthropic | $19.48 | $68.20 | 400,000 | 87.7 |
| 9 | o4 Max | OpenAI | $19.51 | $93.98 | 2,000,000 | 86.2 |
| 10 | Gemini 3 Pro Pro | Google DeepMind | $19.80 | $108.61 | 200,000 | 87.3 |
| 11 | Gemini 3 Pro | Google DeepMind | $18.24 | $82.93 | 2,000,000 | 86.1 |
| 12 | GPT-5.2 Vision | OpenAI | $19.03 | $85.72 | 1,000,000 | 87.4 |
| 13 | Claude Opus 4.5 Reasoning | Anthropic | $20.91 | $108.13 | 2,000,000 | 88.2 |
| 14 | GPT-5.1 Pro | OpenAI | $19.77 | $100.32 | 200,000 | 87.8 |
| 15 | GPT-5.2 Turbo | OpenAI | $20.73 | $96.05 | 1,000,000 | 87.4 |
| 16 | o4 Pro | OpenAI | $19.37 | $70.19 | 1,000,000 | 87.3 |
| 17 | Grok 4 | xAI | $17.90 | $84.75 | 200,000 | 86.5 |
| 18 | Gemini 3 Pro Max | Google DeepMind | $20.57 | $112.92 | 2,000,000 | 87.9 |
| 19 | Claude Opus 4.5 Max | Anthropic | $20.90 | $106.51 | 1,000,000 | 87.8 |
| 20 | Grok 4 Turbo | xAI | $19.21 | $87.37 | 1,000,000 | 86.7 |
Methodology
This story uses the AI & LLM Index dataset: 600 models, 40 providers and 12 benchmarks. Prices are listed per million tokens. Scores are modelled estimates on a 0–100 scale and are not official benchmark results. Figures are rounded for readability.
Related
FAQ
What does the Best coding models in 2026 data show?
The strongest coding models in the index, ranked by the average of SWE-bench Verified, HumanEval, LiveCodeBench.
Are the numbers official?
No. Prices and scores are compiled for this demo index. Benchmark values are modelled estimates, not official results. Verify figures with the provider or benchmark owner before making decisions.
How should I use this ranking?
Use it to form a shortlist. Check the specific model pages, compare price and context, and test the shortlist on your own examples before committing.