IR Compliance Evaluation on IR Compliance NGFT
0Self Violation RateGem.-2-Pro
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Gem.-2-ProRole=Buyer2026.04 | 0 | 0 | |
| o3Role=Seller2026.04 | 0 | 0.6 | |
| DeepSeek-V3Role=Buyer2026.04 | 0.1 | 0.4 | |
| o3Role=Buyer2026.04 | 0.1 | 5 | |
| GPT-4oRole=Buyer2026.04 | 0.2 | 0.1 | |
| Gem.-2-FlashRole=Buyer2026.04 | 0.4 | 0 | |
| DeepSeek-V3Role=Seller2026.04 | 0.6 | 0 | |
| Gem.-2-ProRole=Seller2026.04 | 0.7 | 0 | |
| Gem.-2-FlashRole=Seller2026.04 | 1.9 | 0 | |
| GPT-4oRole=Seller2026.04 | 2.3 | 0.2 |