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 Korea South. Source: Global Dialogues GD4 (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 | 2nd 66.0% | 4th 63.7% | 1st 66.1% | 6th 57.8% | 5th 59.4% | 3rd 63.9% | |
| 51.8% | 54% | 61% | 58% | 40% | 43% | 55% | |
| 67.0% | 68% | 70% | 67% | 67% | 63% | ||
| 69.2% | 72% | 83% | 76% | 59% | 59% | 66% | |
| 64.0% | 79% | 57% | 66% | 54% | 57% | 71% | |
| 69.5% | 70% | 60% | 77% | 72% | 68% | 70% | |
| 67.2% | 62% | 74% | 71% | 66% | 60% | 70% | |
| 36.5% | 36% | 20% | 53% | 20% | 46% | 44% | |
| 69.3% | 76% | 76% | 69% | 65% | 62% | 68% | |
| 63.5% | 62% | 62% | 61% | 63% | 70% | 63% | |
| 70.3% | 81% | 74% | 64% | 72% | 62% | 69% |