Financial Knowledge Capability on FLameCer
94.71ScoreQianfanHuijin-70B
Evaluation results
| Method | Links | ||
|---|---|---|---|
| QianfanHuijin-70BEvaluation Mode=Non-Thinking, Model Scale=70B2025.12 | 94.71 | 89.69 | |
| QianfanHuijin-70BModel Scale=70B+, Mode=Thinking2025.12 | 94.43 | 86.2 | |
| Qwen3-235BModel Scale=70B+, Mode=Thinking2025.12 | 90.14 | 82.61 | |
| Qwen3-235BEvaluation Mode=Non-Thinking, Model Scale=235B2025.12 | 89.14 | 88.26 | |
| DeepSeek-R1Model Scale=70B+, Mode=Thinking2025.12 | 89 | 82.56 | |
| DeepSeek-V3.2Model Scale=70B+, Mode=Thinking2025.12 | 88.71 | 83.82 | |
| DeepSeek-V3Evaluation Mode=Non-Thinking2025.12 | 88.71 | 87.6 | |
| DeepSeek-V3.2Evaluation Mode=Non-Thinking2025.12 | 86.7 | 85.88 | |
| QianfanHuijin-8BModel Scale=8B, Mode=Thinking2025.12 | 86.14 | 81.47 | |
| QianfanHuijin-8BEvaluation Mode=Non-Thinking, Model Scale=8B2025.12 | 78.43 | 80.76 | |
| Qwen3-8BModel Scale=8B, Mode=Thinking2025.12 | 78.1 | 75.88 | |
| DianJin-R1-7BModel Scale=8B, Mode=Thinking2025.12 | 77.2 | 71.85 | |
| Qwen3-8BEvaluation Mode=Non-Thinking, Model Scale=8B2025.12 | 76.57 | 74.21 |