Benchmark
FinBen BigData22 F1
Scores are percentages. Higher is better.
Benchmark sourceScores from TheFinAI public numeric results.
- Models measured
- 2
- Scores recorded
- 2
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 44.2%
- Mean
- 50.4%
- Median
- 6.2%
- Std dev
- 37.9%
- 10th percentile
- 50.4%
- 90th percentile
- 37.9%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | code-llama-7b-instructpublished-demo-leaderboard, BigData22, F1· TheFinAI public numeric results | 50.4% |
| 2 | Llama 3.2 3Bpublished-demo-leaderboard, BigData22, F1· TheFinAI public numeric results | 37.9% |