Carlini Applied LLM Benchmark: leaderboard
Nicholas Carlini's practical coding benchmark with ~100 tests covering real-world tasks like parsing BNF grammars, writing shell one-liners, and generating C programs.
Metric: Pass Rate (%). Source: github.com. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O1 Mini | 62 | #323 |
| 2 | Claude 3.5 Sonnet | 56 | #350 |
| 3 | GPT-4o | 48 | #343 |
| 4 | Gemini 1.5 Pro | 43 | #445 |
| 5 | Claude 3 Opus | 42 | #571 |
| 6 | GPT-4o Mini | 36 | #599 |
| 7 | Mistral Large | 28 | #710 |
| 8 | GPT-3.5 | 26 | #818 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=carlini-applied-llm-benchmark · How It Works · Data refreshed daily, snapshot 2026-10-20.