Benchmark
FinBen EDTSUM BertScore
Higher scores are better.
Benchmark sourceScores from TheFinAI public numeric results.
- Models measured
- 9
- Scores recorded
- 9
- Sources
- 1
- IQ weight
- 0.75
Score distribution
- 0.654
- Mean
- 0.663
- Median
- 0.037
- Std dev
- 0.61
- 10th percentile
- 0.68
- 90th percentile
- 0.596
- Min
This benchmark has a weight of 0.75 for chat models, measured over 9 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 | gemini-1.0-propublished-demo-leaderboard, EDTSUM, BertScore· TheFinAI public numeric results | 0.72 |
| 2 | Llama 2 70bpublished-demo-leaderboard, EDTSUM, BertScore· TheFinAI public numeric results | 0.68 |
| 3 | GPT-4 Turbopublished-demo-leaderboard, EDTSUM, BertScore· TheFinAI public numeric results | 0.67 |
| 4 | Qwen2 7B Instructpublished-demo-leaderboard, EDTSUM, BertScore· TheFinAI public numeric results | 0.67 |
| 5 | DeepSeek V3published-demo-leaderboard, EDTSUM, BertScore· TheFinAI public numeric results | 0.663 |
| 6 | GPT-3.5 Turbopublished-demo-leaderboard, EDTSUM, BertScore· TheFinAI public numeric results | 0.66 |
| 7 | Llama-2-7b-chat-hfpublished-demo-leaderboard, EDTSUM, BertScore· TheFinAI public numeric results | 0.62 |
| 8 | Mixtral 8X7b V0.1published-demo-leaderboard, EDTSUM, BertScore· TheFinAI public numeric results | 0.61 |
| 9 | DeepSeek R1 Distill Qwen 7Bpublished-demo-leaderboard, EDTSUM, BertScore· TheFinAI public numeric results | 0.596 |