Gorilla Benchmark API Bench
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.
3rows
scoreprimary metric
2026-05-06sampled
Metadata
Metrics
Score, Normalized Score
| Rank | Subject | Score | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | Llama 3.1 405B Instruct | 0.35 | — | Self-reported | 2026-05-06 |
| 2 | Llama 3.1 70B Instruct | 0.30 |  Llama 3.1 70B Instruct meta-llama-llama-3.1-70b-instruct | Self-reported | 2026-05-06 |
| 3 | Llama 3.1 8B Instruct | 0.08 | Llama 3.1 8B Instruct meta-llama-llama-3.1-8b-instruct | Self-reported | 2026-05-06 |
No matching rows.