Most used in coding agents
The models people ran most inside coding agents (Claude Code, Codex, OpenCode and others) over the last 30 days, by share of turns in T3 Code's usage telemetry. One client's users, not the whole market.
As of 9 Nov 2026, Claude Opus 5.5 by Anthropic leads this list (57.1%), ahead of GPT-6.1 Sol (19.2%).
26 models qualify · data as of 9 Nov 2026
- 1Claude Opus 5.5 (max)57.1%
- 2GPT-6.1 Sol (max)19.2%
- 3GPT-6 Astra5.1%
- 4Claude Sonnet 5.5 (max)3.8%
- 5Claude Fable 5.1 (max)2.0%
- 6GPT-6 Luna (max)1.3%
- 7GPT-6.1 Terra (max)0.9%
- 8Claude Haiku 5.5 (max)0.9%
- 9GPT-6 Sol (max)0.2%
- 10GPT-5.6 Sol (max)0.2%
- 11Claude Opus 50.1%
- 12GPT-5.6 Luna (xhigh)0.1%
- 13Gemini 3.8 Flash (high)0.1%
- 14Claude Opus 4.8 (high)0.1%
- 15GPT-5.6 Terra (max)0.1%
26 of 26
| # | |||||
|---|---|---|---|---|---|
| 1 | 57.1% | 68.9 | $8.00 | 115 | |
| 2 | 19.2% | 67.0 | $4.00 | 57 | |
| 3 | 5.1% | 68.1 | $20.00 | 27 | |
| 4 | 3.8% | 65.0 | $4.00 | 152 | |
| 5 | 2.0% | 66.9 | $20.00 | 87 | |
| 6 | 1.3% | 56.5 | $0.200 | 104 | |
| 7 | 0.9% | 65.0 | $2.00 | 73 | |
| 8 | 0.9% | 56.8 | $0.200 | 238 | |
| 9 | 0.2% | 62.9 | $4.00 | 121 | |
| 10 | 0.2% | 65.4 | $8.00 | 99 | |
| 11 | 0.1% | 65.2 | $10.00 | 64 | |
| 12 | 0.1% | 58.4 | $0.450 | 102 | |
| 13 | 0.1% | 61.8 | $1.50 | 112 | |
| 14 | 0.1% | 60.5 | $10.00 | 71 | |
| 15 | 0.1% | 60.5 | $4.50 | 106 | |
| 16 | 0.1% | 59.2 | $4.00 | 105 | |
| 17 | 0.0% | 58.2 | $6.00 | 44 | |
| 18 | 0.0% | 62.7 | $10.00 | 39 | |
| 19 | 0.0% | 66.6 | $20.00 | 55 | |
| 20 | 0.0% | 47.6 | $2.00 | 90 | |
| 21 | 0.0% | 64.3 | $11.25 | 80 | |
| 22 | 0.0% | 63.2 | $5.63 | 73 | |
| 23 | 0.0% | 63.2 | $10.00 | 48 | |
| 24 | 0.0% | 59.7 | $10.00 | 67 | |
| 25 | 0.0% | 56.0 | $1.69 | 198 | |
| 26 | 0.0% | – | $3.44 | 98 |