Meeting Information Extraction on Merged Typed Benchmark 113 meetings (Pairwise Evaluation)
-0.139Mean Differencegpt-41-mini vs gpt-51
Evaluation results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| gpt-41-mini vs gpt-51Metric=Coverage2026.04 | -0.139 | — | — | — | 3 | 11 | 99 | 2.09 | — | |
| gpt-41-mini vs gpt-5-miniMetric=Coverage2026.04 | -0.072 | — | — | — | 15 | 21 | 77 | 3.26 | — | |
| gpt-41-mini vs gpt-51Metric=Completeness2026.04 | -0.071 | — | — | — | 3 | 1 | 109 | 2.71 | — | |
| gpt-5-mini vs gpt-51Metric=Coverage2026.04 | -0.067 | — | — | — | 11 | 17 | 85 | 5.1 | — | |
| gpt-5-mini vs gpt-51Metric=Completeness2026.04 | -0.043 | — | — | — | 9 | 1 | 103 | 4.63 | — | |
| gpt-41-mini vs gpt-5-miniMetric=Completeness2026.04 | -0.028 | — | — | — | 20 | 2 | 91 | 5.25 | — | |
| gpt-41-mini vs gpt-5-miniMetric=Accuracy2026.04 | 0.006 | — | — | — | 60 | 2 | 51 | 0.4478 | — | |
| gpt-5-mini vs gpt-51Metric=Accuracy2026.04 | 0.021 | — | — | — | 64 | 2 | 47 | 0.257 | — | |
| gpt-41-mini vs gpt-51Metric=Accuracy2026.04 | 0.027 | — | — | — | 69 | 1 | 43 | 0.0533 | — |