pingdotgg/
Run by mupt-ai · Released 2026-10-02 · 33 tasks · 9 settings
Which coding agent works best on pingdotgg/t3code? Most accurate: Claude Opus 5.5, 78.8% at $1.53 per task. Best for less: GLM 5.3 Flash, 69.7% at $0.22. 9 model settings scored on 33 tasks from its merged pull requests.
All Settings
| Model | Harness | Reasoning | Access | Accuracy | Cost / Task | Frontier |
|---|---|---|---|---|---|---|
| Claude Opus 5.5 | Claude Code | High | API Key | 78.8% | $1.53 | Yes |
| GLM 5.3 Flash | Pi | High | Vercel AI Gateway | 69.7% | $0.22 | Yes |
| GPT-6.1 Sol | Codex | Low | API Key | 69.7% | $0.26 | No |
| GPT-6.1 Sol | Codex | High | API Key | 69.7% | $0.51 | No |
| Claude Sonnet 5.5 | Claude Code | High | API Key | 60.6% | $0.57 | No |
| Kimi K3 | Pi | High | Vercel AI Gateway | 57.6% | $1.54 | No |
| GPT-6 Luna | Codex | High | API Key | 51.5% | $0.031 | Yes |
| GLM 5.3 | Codex | High | Vercel AI Gateway | 51.5% | $2.14 | No |
| GPT-6 Luna | Codex | Low | API Key | 27.3% | $0.032 | No |