Skip to content

Benchmark

API-Bank

Scores are percentages. Higher is better.

Models measured
3
Scores recorded
4
Sources
2
IQ weight
No weight published

Score distribution

88.7%
Mean
90%
Median
3.6%
Std dev
82.6%
10th percentile
92%
90th percentile
82.6%
Min
82.6%92%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Llama 3.1 405B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim92%
2Llama 3.1 70B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90%
3Llama 3.1 70B Instructofficial instruction-tuned table· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90%
4Llama 3.1 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim82.6%

Data credits: Data by LLM Stats · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.