Troubleshooting on TS FloDial weighted (test)
113.6Worst-case Weighted PayoffDC
Evaluation results
| Method | Links | |
|---|---|---|
| DCBackbone LLM=Qwen 2.5 72B Instruct2026.02 | 113.6 | |
| DCBackbone LLM=GPT 4.12026.02 | 97.4 | |
| DPBackbone LLM=GPT 4.12026.02 | 90.1 | |
| UoTBackbone LLM=GPT 4.12026.02 | 81 | |
| DPBackbone LLM=Qwen 2.5 72B Instruct2026.02 | 80 | |
| UoTBackbone LLM=Qwen 2.5 72B Instruct2026.02 | 74 | |
| GoTBackbone LLM=Qwen 2.5 72B Instruct2026.02 | 62.3 | |
| GoTBackbone LLM=GPT 4.12026.02 | 61.4 |