Benchmark
LAMBADA
Scores are percentages.
All general benchmarksScores from Epoch AI Benchmarking Hub data.
- Models measured
- 5
- Scores recorded
- 5
- Sources
- 1
- IQ weight
- 2.46
Score distribution
- 73.1%
- Mean
- 75.2%
- Median
- 10.5%
- Std dev
- 54.3%
- 10th percentile
- 86.4%
- 90th percentile
- 54.3%
- Min
This benchmark has a weight of 2.46 for chat models, measured over 5 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | text-davinci-001· Epoch AI Benchmarking Hub data | 86.4% |
| 2 | Llama 2 13b· Epoch AI Benchmarking Hub data | 76.5% |
| 3 | LLaMA 13B· Epoch AI Benchmarking Hub data | 75.2% |
| 4 | Llama 2 7b· Epoch AI Benchmarking Hub data | 73.3% |
| 5 | ChatGLM2 6B· Epoch AI Benchmarking Hub data | 54.3% |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)