AI Coding Daily (OpenCode) - Laravel Code Quality: leaderboard
Laravel project code quality on AI Coding Daily's LLM Coding Leaderboard for runs in the OpenCode harness: a 100-point rubric score from a fixed LLM judge (gpt-5.6-sol at medium effort in Codex CLI) divided by five, maximum 20; higher is better. The judge is an OpenAI model, so self-preference is possible.
Metric: Laravel Code Quality (max 20) points, LLM-judged rubric score / 5. Source: aicodingdaily.com. Saturation forecast: Estimated already saturated. 22 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K3.1 Pro (Max) | 18.55 | #17 (Kimi K3.1 Pro) |
| 2 | DeepSeek V4.1 Flash (1017) (High) | 17.98 | #27 (DeepSeek V4.1 Flash (1017)) |
| 3 | mistral-large-4-oss (High) | 17.78 | #60 (mistral-large-4-oss) |
| 4 | Kimi K3.1 Pro (High) | 17.7 | #17 (Kimi K3.1 Pro) |
| 5 | GLM-5.3 (High) | 17.55 | #44 (GLM-5.3) |
| 6 | MiniMax-M3.1-Flash (Max) | 17.44 | #52 (MiniMax-M3.1-Flash) |
| 7 | DeepSeek V4.1 Flash (1017) (Max) | 17.42 | #27 (DeepSeek V4.1 Flash (1017)) |
| 8 | DeepSeek V4 Pro (0813) (Max) | 17.3 | #58 (DeepSeek V4 Pro (0813)) |
| 9 | DeepSeek V4 Pro (0813) (High) | 17.25 | #58 (DeepSeek V4 Pro (0813)) |
| 10 | Qwen 3.8 27B (xHigh) | 17.23 | #123 (Qwen 3.8 27B) |
| 11 | GLM-5.3 Flash (Max) | 17.2 | #77 (GLM-5.3 Flash) |
| 12 | Hy3 (High) | 16.8 | #100 (Hy3) |
| 13 | Qwen 3.8 Flash (Max) | 16.35 | #62 (Qwen 3.8 Flash) |
| 14 | Mercury 3 (High) | 16.08 | #78 (Mercury 3) |
| 15 | Muse Spark 1.3 (Max) | 15.6 | #31 (Muse Spark 1.3) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=ai-coding-daily-opencode-laravel-code-quality · How It Works · Data refreshed daily, snapshot 2026-11-05.