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 GD3 (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 65.1% | 1st 65.8% | 6th 57.2% | 4th 61.3% | 5th 58.9% | 3rd 62.7% | |
| 58.0% | 54% | 67% | 57% | 45% | 71% | 54% | |
| 56.2% | 53% | 58% | 53% | 62% | 52% | 59% | |
| 61.0% | 67% | 64% | 53% | 60% | 65% | 57% | |
| 75.8% | 80% | 69% | 69% | 72% | 93% | 72% | |
| 38.2% | 34% | 62% | 35% | 39% | 25% | 34% | |
| 69.0% | 66% | 71% | 67% | 76% | 62% | 72% | |
| 57.2% | 65% | 61% | 58% | 60% | 44% | 55% | |
| 78.8% | 82% | 78% | 75% | 80% | 80% | 78% | |
| 63.0% | 75% | 74% | 62% | 52% | 35% | 80% | |
| 61.2% | 75% | 54% | 43% | 67% | 62% | 66% |