Best Google Gemini model for coding
- models ranked
- 15
- lead over #2
- +2.6
Coding index · read October 21
As of October 21, 2026, Google Gemini 2.5 Pro Preview 06-05 leads 15 scored Google models with a coding index of 83.1, ahead of Google Gemini 4 Argon (80.5) and Google Gemini 3 Flash Preview (75.8).
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 | Gemini 2.5 Pro Preview 06-05 Google | 83.1 | $10.00 | |
| 2 | Gemini 4 Argon Google | 80.5 | $10.00 | |
| 3 | Gemini 3 Flash Preview Google | 75.8 | $3.00 | |
| 4 | Gemini 3.8 Flash Google | 70.5 | $4.125 | |
| 5 | Gemini 3.7 Flash Google | 69.9 | $3.75 | |
| 6 | Gemini 3.6 Flash Google | 48.3 | $3.75 | |
| 7 | Gemini 3.5 Flash Google | 42.8 | $9.00 | |
| 8 | Gemma 4 31B Google | 38.3 | $0.40 | |
| 9 | Gemini 2.5 Pro Google | 37.0 | $10.00 | |
| 10 | Gemini 3.1 Pro Preview Google | 35.3 | $12.00 | |
| 11 | Gemini 3.5 Flash Lite Google | 33.6 | $2.50 | |
| 12 | Gemini 2.5 Flash Google | 28.7 | $2.50 | |
| 13 | Gemma 4 26B A4B Google | 22.8 | $0.255 | |
| 14 | 8.1 | $1.50 | ||
| 15 | Gemma 3 27B Google | 4.9 | $0.35 |
How this list is built
Generated from the dataset on every refresh. Nobody picks the order by hand.
Every Google 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