Best OpenAI model for coding
- GPT-6 Astra leads
- 88.7
- models ranked
- 33
Coding index · read October 21
As of October 21, 2026, OpenAI GPT-6 Astra leads 33 scored OpenAI models with a coding index of 88.7, ahead of OpenAI GPT-6.1 Sol (88.7) and OpenAI o3 Pro (84.9).
This list narrows the best LLM for coding ranking.
Ordered by index, highest first. The dots show how many benchmarks stand behind each score.
| Rank | Model | Coding index | Evidence | Output $/Mtok |
|---|---|---|---|---|
| 1 | GPT-6 Astra OpenAI | 88.7 | $50.00 | |
| 2 | GPT-6.1 Sol OpenAI | 88.7 | $10.00 | |
| 3 | o3 Pro OpenAI | 84.9 | $80.00 | |
| 4 | GPT-6 Sol OpenAI | 82.8 | $10.00 | |
| 5 | GPT-5.6 Sol OpenAI | 76.7 | $20.00 | |
| 6 | GPT-5 OpenAI | 72.2 | $10.00 | |
| 7 | GPT-6 Luna OpenAI | 71.4 | $0.50 | |
| 8 | o3 OpenAI | 70.7 | $8.00 | |
| 9 | GPT-5.6 Terra OpenAI | 69.0 | $12.00 | |
| 10 | o4 Mini OpenAI | 68.6 | $4.40 | |
| 11 | GPT-5.5 OpenAI | 67.8 | $30.00 | |
| 12 | o1 OpenAI | 61.7 | $60.00 | |
| 13 | GPT-5.6 Luna OpenAI | 61.5 | $1.20 | |
| 14 | GPT-5 Mini OpenAI | 59.8 | $2.00 | |
| 15 | GPT-5.2 OpenAI | 58.9 | $14.00 | |
| 16 | GPT-5.2-Codex OpenAI | 55.1 | $14.00 | |
| 17 | GPT-5.1 OpenAI | 53.3 | $10.00 | |
| 18 | o3 Mini OpenAI | 52.1 | $4.40 | |
| 19 | GPT-5.1-Codex OpenAI | 50.5 | $10.00 | |
| 20 | GPT-4.1 OpenAI | 46.5 | $8.00 |
How this list is built
Generated from the dataset on every refresh. Nobody picks the order by hand.
Every OpenAI model with a Vibe Coding Index score, ordered as the ranking orders them: by how many benchmarks stand behind the score, then by the score.
- Aider polyglot leaderboard, fetched
- LiveBench, fetched , board updated October 14, 2026
- SWE-bench (swebench.com), fetched
- LMArena WebDev, fetched