Online Drama Performance Evaluation on HAMLET Chinese
80.18Character ScoreClaude-4-sonnet
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Claude-4-sonnetModel Reasoning Category=Non-Reasoning Models, Sampling Strategy=greedy2025.07 | 80.18 | 79.2 | 79.66 | 79.68 | |
| DeepSeek-R1-0528Model Reasoning Category=Reasoning Models, Sampling Strategy=greedy2025.07 | 79 | 79.5 | 79.61 | 79.37 | |
| Claude-4-sonnet-ThinkingModel Reasoning Category=Reasoning Models, Sampling Strategy=greedy2025.07 | 78.42 | 80.32 | 81.03 | 79.92 | |
| OpenAI-o3Model Reasoning Category=Reasoning Models, Sampling Strategy=greedy2025.07 | 78 | 77.5 | 78.17 | 77.89 | |
| Qwen3-32B-ThinkingModel Reasoning Category=Reasoning Models, Sampling Strategy=greedy2025.07 | 78 | 79 | 78.77 | 78.59 | |
| Claude-3.7-sonnetModel Reasoning Category=Non-Reasoning Models, Sampling Strategy=greedy2025.07 | 76 | 75.2 | 75.48 | 75.56 | |
| Qwen3-235B-A22B-ThinkingModel Reasoning Category=Reasoning Models, Sampling Strategy=greedy2025.07 | 76 | 75.8 | 75.96 | 75.92 | |
| Qwen3-235B-A22BModel Reasoning Category=Non-Reasoning Models, Sampling Strategy=greedy2025.07 | 72.5 | 73 | 72.78 | 72.76 | |
| Qwen3-32BModel Reasoning Category=Non-Reasoning Models, Sampling Strategy=greedy2025.07 | 66 | 65.5 | 65.84 | 65.78 | |
| Qwen3-8B-ThinkingModel Reasoning Category=Reasoning Models, Sampling Strategy=greedy2025.07 | 65.8 | 65 | 65.55 | 65.45 | |
| Minimax-M1Model Reasoning Category=Reasoning Models, Sampling Strategy=greedy2025.07 | 65 | 65.5 | 65.19 | 65.23 | |
| DeepSeek-V3-0324Model Reasoning Category=Non-Reasoning Models, Sampling Strategy=greedy2025.07 | 64.5 | 64 | 64.01 | 64.17 | |
| Higgs-Llama-3-70BModel Reasoning Category=Non-Reasoning Models, Sampling Strategy=greedy2025.07 | 64 | 64.5 | 63.95 | 64.15 | |
| GPT-4.1Model Reasoning Category=Non-Reasoning Models, Sampling Strategy=greedy2025.07 | 62 | 62.8 | 62.64 | 62.48 | |
| Gemini-2.5-proModel Reasoning Category=Reasoning Models, Sampling Strategy=greedy2025.07 | 62 | 62.8 | 62.25 | 62.35 | |
| GPT-4.5-previewModel Reasoning Category=Non-Reasoning Models, Sampling Strategy=greedy2025.07 | 61.5 | 62.5 | 61.91 | 61.97 | |
| Claude-3.5-sonnetModel Reasoning Category=Non-Reasoning Models, Sampling Strategy=greedy2025.07 | 60.5 | 59 | 59.99 | 59.83 | |
| Magistral-Small-2506Model Reasoning Category=Reasoning Models, Sampling Strategy=greedy2025.07 | 58.5 | 59.3 | 58.9 | 58.9 | |
| Qwen3-8BModel Reasoning Category=Non-Reasoning Models, Sampling Strategy=greedy2025.07 | 58 | 57.5 | 58.05 | 57.85 | |
| Gemini-2.5-flashModel Reasoning Category=Non-Reasoning Models, Sampling Strategy=greedy2025.07 | 52 | 52.9 | 52.15 | 52.35 | |
| Mistral-Small-3.2-24BModel Reasoning Category=Non-Reasoning Models, Sampling Strategy=greedy2025.07 | 51 | 51.83 | 52 | 51.61 | |
| Llama-3.1-70BModel Reasoning Category=Non-Reasoning Models, Sampling Strategy=greedy2025.07 | 42 | 42.81 | 42 | 42.27 | |
| Llama-3.1-8BModel Reasoning Category=Non-Reasoning Models, Sampling Strategy=greedy2025.07 | 33.5 | 34 | 33.99 | 33.83 |