Loading blueprint versions...
Please wait while we gather all the unique runs for this blueprint.
Please wait while we gather all the unique runs for this blueprint.
Please wait while we prepare the detailed comparison.
DTEF: Predict response distributions for More excited than concerned. Source: Global Dialogues GD7 (https://github.com/collect-intel/global-dialogues)
Average key point coverage extent for each model across all prompts.
| Prompts vs. Models | Claude Haiku 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o Mini | |
|---|---|---|---|---|---|---|---|
| Score | 3rd 78.9% | 5th 72.0% | 4th 73.7% | 2nd 79.7% | 1st 80.5% | 6th 71.8% | |
| 72.3% | 71% | 57% | 70% | 85% | 78% | 73% | |
| 76.0% | 83% | 68% | 71% | 81% | 82% | 71% | |
| 84.8% | 84% | 90% | 84% | 82% | 92% | 77% | |
| 71.7% | 66% | 64% | 70% | 74% | 83% | 73% | |
| 79.2% | 85% | 77% | 82% | 82% | 82% | 67% | |
| 71.0% | 84% | 72% | 69% | 75% | 53% | 73% | |
| 75.2% | 79% | 81% | 67% | 83% | 80% | 61% | |
| 65.8% | 75% | 49% | 77% | 58% | 73% | 63% | |
| 81.2% | 84% | 81% | 70% | 85% | 92% | 75% | |
| 83.8% | 78% | 81% | 77% | 92% | 90% | 85% |