Benchmark
FinBen TSA-Spanish MCC
Higher scores are better.
Benchmark sourceScores from TheFinAI public numeric results.
- Models measured
- 6
- Scores recorded
- 6
- Sources
- 1
- IQ weight
- 1.20
Score distribution
- 0.141
- Mean
- 0.082
- Median
- 0.132
- Std dev
- 0.047
- 10th percentile
- 0.325
- 90th percentile
- 0.0074
- Min
This benchmark has a weight of 1.20 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, MCC· TheFinAI public numeric results | 0.325 |
| 2 | Qwen2.5 7Bpublished-demo-leaderboard, TSA-Spanish, MCC· TheFinAI public numeric results | 0.325 |
| 3 | Qwen2.5 7B Instructpublished-demo-leaderboard, TSA-Spanish, MCC· TheFinAI public numeric results | 0.0819 |
| 4 | codellama-7bpublished-demo-leaderboard, TSA-Spanish, MCC· TheFinAI public numeric results | 0.0583 |
| 5 | Llama 3.2 3Bpublished-demo-leaderboard, TSA-Spanish, MCC· TheFinAI public numeric results | 0.0465 |
| 6 | code-llama-7b-instructpublished-demo-leaderboard, TSA-Spanish, MCC· TheFinAI public numeric results | 0.0074 |