Effectiveness Scoring on AMI Corpus Non-Scenario Meetings
0.4564Spearman's ρQwen3-32B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Qwen3-32BReasoning mode=non-reasoning, Input configuration=ground truth inputs, Context window size=12026.04 | 0.4564 | 0.3347 | |
| DeepSeek-R1-70BInput configuration=ground truth inputs, Context window size=12026.04 | 0.3852 | 0.3012 | |
| Qwen3-32BReasoning mode=reasoning, Input configuration=ground truth inputs, Context window size=12026.04 | 0.3193 | 0.2456 | |
| GPT-4oInput configuration=ground truth inputs, Context window size=12026.04 | 0.2873 | 0.2074 | |
| Llama3.3-70B-InstructInput configuration=ground truth inputs, Context window size=12026.04 | 0.2411 | 0.2031 | |
| Gemini-2.5-FlashInput configuration=ground truth inputs, Context window size=12026.04 | 0.1845 | 0.1289 |