EffiBench - NET Leaderboard — LLM Benchmark Hub

EffiBench - NET — leaderboard

Metric: Normalized Execution Time. Source: huggingface.co. 24 models tracked.

Top models

#	Model	Score
1	starcoder2-15B	2.59
2	CodeLlama-13B-hf	2.71
3	Yi 34B (Chat)	2.77
4	Yi 34B (Base)	2.81
5	deepseek-coder-1.3B-instruct	2.82
6	starcoder	2.84
7	deepseek-coder-6.7B-instruct	2.89
8	starcoder2-3B	2.9
9	Yi-34B-200K	2.91
10	CodeLlama-13B-Instruct-hf	2.93
11	CodeLlama-7B-hf	2.95
12	CodeLlama-34B-hf	2.98
13	deepseek-coder-6.7B-base	2.98
14	starcoder2-7B	3.02
15	CodeLlama-34B-Instruct-hf	3.04

Interactive version: aibenchmarks.dev/benchmark?slug=effibench-net · How the rankings work · Data refreshed daily, snapshot 2026-07-17.