CodeEditorBench Plus - Code Translate (Zero-shot): leaderboard

Metric: pass@1 (%, greedy decoding, zero-shot, CodeEditorBench_Plus). Source: codeeditorbench.github.io. Saturation forecast: Estimated already saturated. 19 models tracked.

Top models

#ModelScore
1GPT-3.5 Turbo (1106)47.5
2GPT-4 (0613)46.5
3Gemini 1.0 Pro34.4
4CodeLlama-13B-Instruct-hf33.3
5CodeLlama-34B-hf31
6WizardCoder-15B-V1.030.9
7CodeLlama-7B-Instruct-hf28.9
8CodeLlama-34B-Instruct-hf28.7
9Phind-CodeLlama-34B-v227.9
10GLM-427.8
11Magicoder-S-CL-7B27.2

Interactive version: theaggregate.ai/benchmark?slug=codeeditorbench-plus-code-translate-zero-shot · How It Works · Data refreshed daily, snapshot 2026-09-26.