CanAiCode: leaderboard
Benchmarks smaller code-focused LLMs on text-to-code performance across multiple languages.
Metric: Junior-v2 Python Pass Rate (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 189 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude 3.5 Sonnet (20240620) | 100 | #299 |
| 2 | GPT-4 Turbo | 100 | #404 |
| 3 | Claude 3 Sonnet (20240229) | 100 | #677 |
| 4 | Claude 3 Opus (20240229) | 100 | #412 |
| 5 | GPT-4 (0613) | 100 | #491 |
| 6 | GPT-4 Preview (0125) | 100 | #486 |
| 7 | GPT-4 Preview (1106) | 100 | #418 |
| 8 | GPT-4o (2024-05-13) | 98.9 | #325 |
| 9 | Claude 3 Haiku (20240307) | 98.9 | #771 |
| 10 | GPT-3.5 Turbo (0125) | 98.9 | #984 |
| 11 | GPT-3.5 Turbo (1106) | 98.9 | #961 |
| 12 | GPT-3.5 Turbo (0613) | 96.7 | #1118 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=canaicode · How It Works · Data refreshed daily, snapshot 2026-10-20.