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 France. Source: Global Dialogues GD5 (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 | 5th 67.1% | 4th 67.6% | 1st 70.7% | 3rd 69.2% | 6th 65.5% | 2nd 69.5% | |
| 70.2% | 56% | 69% | 75% | 74% | 74% | 73% | |
| 66.5% | 68% | 61% | 70% | 68% | 66% | 66% | |
| 76.7% | 79% | 82% | 70% | 81% | 72% | 76% | |
| 87.0% | 91% | 95% | 93% | 84% | 67% | 92% | |
| 58.2% | 57% | 55% | 55% | 63% | 55% | 64% | |
| 70.7% | 63% | 68% | 76% | 76% | 70% | 71% | |
| 72.2% | 72% | 71% | 74% | 76% | 72% | 68% | |
| 63.7% | 61% | 68% | 69% | 58% | 64% | 62% | |
| 54.5% | 52% | 49% | 60% | 53% | 57% | 56% | |
| 63.2% | 72% | 58% | 65% | 59% | 58% | 67% |