LLM Stats (Natural2Code): leaderboard
Natural language to code generation benchmark testing the ability to translate informal descriptions into working programs.
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.0 Flash | 92.9 | #342 |
| 2 | Gemini 1.5 Pro | 85.4 | #445 |
| 3 | Gemma 3 27B | 84.5 | #607 |
| 4 | Gemma 3 12B | 80.7 | #671 |
| 5 | Gemini 1.5 Flash | 79.8 | #618 |
| 6 | Gemini 1.5 Flash-8B | 75.5 | #819 |
| 7 | Gemma 3 4B | 70.3 | #1089 |
| 8 | Gemma 3 1B | 56 | #1528 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-natural2code · How It Works · Data refreshed daily, snapshot 2026-10-20.