Benchmark
FinBen TSA-Spanish 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
- 1.26
Score distribution
- 19.9%
- Mean
- 11.7%
- Median
- 17.6%
- Std dev
- 6.1%
- 10th percentile
- 44.6%
- 90th percentile
- 5.9%
- Min
This benchmark has a weight of 1.26 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 | Mistral (7B) Instruct v0.3published-demo-leaderboard, TSA-Spanish, Macro F1· TheFinAI public numeric results | 44.6% |
| 2 | Qwen2.5 7Bpublished-demo-leaderboard, TSA-Spanish, Macro F1· TheFinAI public numeric results | 44.6% |
| 3 | Qwen2.5 7B Instructpublished-demo-leaderboard, TSA-Spanish, Macro F1· TheFinAI public numeric results | 11.7% |
| 4 | code-llama-7b-instructpublished-demo-leaderboard, TSA-Spanish, Macro F1· TheFinAI public numeric results | 6.2% |
| 5 | codellama-7bpublished-demo-leaderboard, TSA-Spanish, Macro F1· TheFinAI public numeric results | 6.1% |
| 6 | Llama 3.2 3Bpublished-demo-leaderboard, TSA-Spanish, Macro F1· TheFinAI public numeric results | 5.9% |