Gorilla Benchmark API Bench

Multilingual: no

APIBench, a comprehensive dataset of over 11,000 instruction-API pairs from HuggingFace, TorchHub, and TensorHub APIs for evaluating language models' ability to generate accurate API calls.

Methodology

Imported from llm-stats public benchmark metadata. Modality: text. Max score: 1. Categories: code, reasoning, tool_calling. Language: en. Verified by llm-stats: no.

Leaderboard

Showing 3 of 3 results

Llama 3.1 405B Instruct self-reported llm-stats

35.3%
Llama 3.1 70B Instruct self-reported llm-stats

29.7%
Llama 3.1 8B Instruct self-reported llm-stats

8.2%