Benchmark
pfgen-bench Japanese generation: Score
Higher scores are better.
Benchmark sourceScores from pfgen-bench (Preferred Networks) data docs.
- Models measured
- 101
- Scores recorded
- 156
- Sources
- 1
- IQ weight
- 1.59
Score distribution
- 0.498
- Mean
- 0.483
- Median
- 0.202
- Std dev
- 0.256
- 10th percentile
- 0.804
- 90th percentile
- 0.0006
- Min
This benchmark has a weight of 1.59 for chat models, measured over 101 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 |
|---|---|---|
| 151 | Qwen1.5-0.5B-Chatqa/chat/822ff8d· pfgen-bench (Preferred Networks) data docs | 0.177 |
| 152 | Yi 1.5 34B Chatcompletion/39ffa65· pfgen-bench (Preferred Networks) data docs | 0.154 |
| 153 | Gemma 2B ITqa/chat/4830586· pfgen-bench (Preferred Networks) data docs | 0.124 |
| 154 | Llama-2-7b-chat-hfqa/chat/18e34ca· pfgen-bench (Preferred Networks) data docs | 0.101 |
| 155 | mistral-nemo-base-2407completion/de5d34b· pfgen-bench (Preferred Networks) data docs | 0.018 |
| 156 | Llama-2-13b-chat-hfcompletion/7b42761· pfgen-bench (Preferred Networks) data docs | 0.0006 |
Showing 151–156 of 156 results.
Data credits: pfgen-bench, Preferred Networks. Apache-2.0 except LLM-generated outputs; aggregate scores only. (licence)