Coding Agent Capacity on CodeSimpleQA
63ScoreClaude-Opus-4.5
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude-Opus-4.52026.06 | 63 | |
| GPT-5.2 High2026.06 | 62.3 | |
| Claude-Sonnet-4.52026.06 | 59.6 | |
| Seed2.0 Pro2026.06 | 58 | |
| GPT-5-mini High2026.06 | 57.6 | |
| Gemini-3-pro High2026.06 | 54.7 | |
| Gemini-3-Flash High2026.06 | 53.7 | |
| Seed2.0 Lite2026.06 | 53.1 |