Claim Verification on FinDVer (test)
76AccuracyMistral-Large
Evaluation results
| Method | Links | |
|---|---|---|
| Mistral-LargeParameters=123B2026.04 | 76 | |
| GPT-4o2026.04 | 76 | |
| MACEBackbone=Qw-235B, Components=Pm + Em2026.04 | 76 | |
| Llama-3.1Parameters=70B2026.04 | 75 | |
| Qwen-2.5Parameters=72B2026.04 | 75 | |
| MACEBackbone=Qw-72B, Components=Pm + Em + Vm2026.04 | 74 | |
| Gemini-1.5-Pro2026.04 | 73 | |
| MACEBackbone=Ll-8B, Components=Pm + Em + Vm'2026.04 | 71 | |
| Qwen-2.52026.04 | 70 | |
| Claude-3.5-Sonnet2026.04 | 70 | |
| MACEBackbone=Mt-7B, Components=Pm + Em + Vm'2026.04 | 65 | |
| DeepSeek-V2-Lite2026.04 | 58 |