Benchmark
FinBen MultiFin-ES Macro F1
Scores are percentages. Higher is better.
Benchmark sourceScores from TheFinAI public numeric results.
- Models measured
- 6
- Scores recorded
- 6
- Sources
- 1
- IQ weight
- 1.56
Score distribution
- 34.5%
- Mean
- 39%
- Median
- 12.1%
- Std dev
- 32.7%
- 10th percentile
- 49.3%
- 90th percentile
- 10.1%
- Min
This benchmark has a weight of 1.56 for chat models, measured over 6 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 | Qwen2.5 7B Instructpublished-demo-leaderboard, MultiFin-ES, Macro F1· TheFinAI public numeric results | 49.3% |
| 2 | Llama 3.2 3Bpublished-demo-leaderboard, MultiFin-ES, Macro F1· TheFinAI public numeric results | 39.7% |
| 3 | codellama-7bpublished-demo-leaderboard, MultiFin-ES, Macro F1· TheFinAI public numeric results | 39.1% |
| 4 | Qwen2.5 7Bpublished-demo-leaderboard, MultiFin-ES, Macro F1· TheFinAI public numeric results | 36.4% |
| 5 | Mistral (7B) Instruct v0.3published-demo-leaderboard, MultiFin-ES, Macro F1· TheFinAI public numeric results | 32.7% |
| 6 | code-llama-7b-instructpublished-demo-leaderboard, MultiFin-ES, Macro F1· TheFinAI public numeric results | 10.1% |