Information Seeking on 20Q Common weighted (test)
235.7Worst-case Weighted PayoffDP
Evaluation results
| Method | Links | |
|---|---|---|
| DPBackbone LLM=Qwen 2.5 72B Instruct2026.02 | 235.7 | |
| UoTBackbone LLM=Qwen 2.5 72B Instruct2026.02 | 228.5 | |
| UoTBackbone LLM=GPT 4.12026.02 | 227.4 | |
| DCBackbone LLM=Qwen 2.5 72B Instruct2026.02 | 225.1 | |
| DPBackbone LLM=GPT 4.12026.02 | 224 | |
| DCBackbone LLM=GPT 4.12026.02 | 199.2 | |
| GoTBackbone LLM=GPT 4.12026.02 | 152.1 | |
| GoTBackbone LLM=Qwen 2.5 72B Instruct2026.02 | 151.9 |