Meeting Summarization on Main merged typed benchmark 114 meetings
58.3Accuracygpt-41-mini
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| gpt-41-miniMeetings=114, Evaluator runs=2282026.04 | 58.3 | 81.4 | 80.4 | |
| gpt-5-miniMeetings=113, Evaluator runs=2262026.04 | 57.4 | 84.3 | 87.5 | |
| gpt-51Meetings=113, Evaluator runs=2262026.04 | 55.3 | 88.6 | 94.2 |