Evaluation profile
FinEval 6.0 Safety Awareness
1sub-evals
0.0395%total index weight
1components
Within-component eval weight: Misuse resistance 0.395%.
Model score (higher is better)Predicted score
About this eval
Safety awareness in financial scenarios.
Included in the behavior ranking.
Sub-evals
| Measure | Component | Direction | Total index weight | Within-component weight |
|---|---|---|---|---|
| safety_awareness_scorefineval/fineval-6-safety-awareness.csv:safety_awareness_scoreMeasures safety awareness in the FinEval 6.0 financial-domain panel. | ordinary_harm_misuse_resistance:1.000fineval-safety | Higher is better | 0.0395% | Misuse resistance 0.395% |
safety_awareness_score
Measures safety awareness in the FinEval 6.0 financial-domain panel.
| Rank | Model | Value | Relative performance | Provenance |
|---|---|---|---|---|
| 1 | llama-3.3-70b-instruct | 83.31 | official | |
| 2 | finix-ci-72b | 82.87 | official | |
| 3 | qwen3-32b | 81.93 | official | |
| 4 | deepseek-r1 | 81.03 | official | |
| 5 | gpt-4o | 79.84 | official | |
| 6 | glm-z1-32b-0414 | 79.16 | official | |
| 7 | internlm3-8b-instruct | 73.52 | official | |
| 8 | qwen3-30b-a3b | 60.51 | official |