Instruct HumanEval

Paper

Progress Over Time

Interactive timeline showing model performance evolution on Instruct HumanEval

State-of-the-art frontier
Open
Proprietary

Instruct HumanEval Leaderboard

1 models
ContextCostLicense
170B
Notice missing or incorrect data?
About this benchmark

What is Instruct HumanEval?

Instruction-based variant of HumanEval benchmark for evaluating large language models' code generation capabilities with functional correctness using pass@k metric on programming problems

Instruct HumanEval is a text benchmark evaluating models on general tasks. LLM Stats tracks 1 models on this benchmark, scored on a 0–1 scale. The current average is 0.7, with the leader at 0.7.

Compare leaders on the best AI for general leaderboards.

Current leaders

Llama 3.1 Nemotron 70B Instruct from NVIDIA currently leads the Instruct HumanEval leaderboard with a score of 0.738 across 1 evaluated AI models.

Source paper

Title
Evaluating Large Language Models Trained on Code
Authors
Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, and 54 others
Published
Abstract

We introduce Codex, a GPT language model fine-tuned on publicly available code from GitHub, and study its Python code-writing capabilities. A distinct production version of Codex powers GitHub Copilot. On HumanEval, a new evaluation set we release to measure functional correctness for synthesizing programs from docstrings, our model solves 28.8% of the problems, while GPT-3 solves 0% and GPT-J solves 11.4%. Furthermore, we find that repeated sampling from the model is a surprisingly effective strategy for producing working solutions to difficult prompts. Using this method, we solve 70.2% of our problems with 100 samples per problem. Careful investigation of our model reveals its limitations, including difficulty with docstrings describing long chains of operations and with binding operations to variables. Finally, we discuss the potential broader impacts of deploying powerful code generation technologies, covering safety, security, and economics.

FAQ

Common questions about the Instruct HumanEval benchmark and leaderboard.

What is the Instruct HumanEval benchmark?

Instruction-based variant of HumanEval benchmark for evaluating large language models' code generation capabilities with functional correctness using pass@k metric on programming problems

What is the Instruct HumanEval leaderboard?

The Instruct HumanEval leaderboard ranks 1 AI models based on their performance on this benchmark. Currently, Llama 3.1 Nemotron 70B Instruct by NVIDIA leads with a score of 0.738. The average score across all models is 0.738.

What is the highest Instruct HumanEval score?

The highest Instruct HumanEval score is 0.738, achieved by Llama 3.1 Nemotron 70B Instruct from NVIDIA.

How many models are evaluated on Instruct HumanEval?

1 models have been evaluated on the Instruct HumanEval benchmark, with 0 verified results and 1 self-reported results.

Where can I find the Instruct HumanEval paper?

The Instruct HumanEval paper is available at https://arxiv.org/abs/2107.03374. The paper details the methodology, dataset construction, and evaluation criteria.

What categories does Instruct HumanEval cover?

Instruct HumanEval is categorized under general. The benchmark evaluates text models.

What is the best open-source model on Instruct HumanEval?

Llama 3.1 Nemotron 70B Instruct by NVIDIA is the top-ranked open-source model on Instruct HumanEval, with a score of 0.738 (rank #1).

How recent are the Instruct HumanEval leaderboard results?

The Instruct HumanEval leaderboard was last updated in July 2026 and currently includes 1 evaluated models.