Kotlin-bench — leaderboard
Kotlin-specific code generation benchmark from Firebender evaluating LLM proficiency in Kotlin programming tasks.
Metric: Pass Rate (%). Source: firebender.com. Status: saturation imminent. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.3 Codex | 49 |
| 2 | Claude Opus 4.5 | 46 |
| 3 | GPT-5.2 | 43 |
| 4 | Gemini 3 Pro | 42 |
| 5 | Gemini 3 Flash | 41 |
| 6 | GPT-5.1 Codex | 41 |
| 7 | Claude Sonnet 4.5 | 37 |
| 8 | GPT-5.2 Codex | 37 |
| 9 | Gemini 3.1 Pro (Preview) | 36 |
| 10 | Kimi K2.5 | 31 |
| 11 | GLM-5 | 30 |
| 12 | Claude Sonnet 4 | 29 |
| 13 | GLM-4.7 | 22 |
| 14 | GLM-4.7 FP8 | 15 |
| 15 | GPT-4.1 | 12 |
Interactive version: theaggregate.ai/benchmark?slug=kotlin-bench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.