C3-Bench (Controllable Code Completion) - Implementation Control - Pass@1: leaderboard
Metric: Pass@1 (%; unit tests on the 1,286 instructed ICC tasks). Source: arxiv.org. Saturation forecast: Estimated already saturated. 42 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O1 (2024-12-17) | 72.1 |
| 2 | Gemini 2.0 Flash | 70.7 |
| 3 | O1 Preview | 70.1 |
| 4 | Claude 3.5 Sonnet (20241022) | 68.8 |
| 5 | GPT-4o (2024-11-20) | 65.9 |
| 6 | GPT-4o (2024-08-06) | 65.8 |
| 7 | O1 Mini | 64.7 |
| 8 | DeepSeek V3 | 61.7 |
| 9 | DeepSeek V3 (0324) | 59.4 |
| 10 | Qwen 2.5 Coder 32B | 58.1 |
| 11 | Qwen 2.5 Coder 14B | 56.1 |
| 12 | GPT-4o (2024-05-13) | 54.3 |
| 13 | Claude 3.5 Haiku | 54.2 |
| 14 | Qwen 2.5 Coder 14B Instruct | 52 |
| 15 | Codestral-22B-v0.1 | 50.5 |
Interactive version: theaggregate.ai/benchmark?slug=c3-bench-controllable-code-completion-implementation-control-pass-1 · How It Works · Data refreshed daily, snapshot 2026-09-25.