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 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 64.3% | 5th 61.5% | 4th 62.4% | 2nd 64.6% | 6th 56.4% | 1st 66.9% | |
| 67.0% | 69% | 65% | 66% | 71% | 57% | 74% | |
| 65.7% | 69% | 65% | 56% | 68% | 68% | 68% | |
| 69.5% | 66% | 71% | 65% | 72% | 71% | 72% | |
| 72.0% | 76% | 65% | 71% | 79% | 60% | 81% | |
| 43.8% | 46% | 43% | 53% | 47% | 31% | 43% | |
| 52.5% | 57% | 57% | 56% | 47% | 39% | 59% | |
| 44.3% | 45% | 43% | 49% | 46% | 35% | 48% | |
| 71.2% | 73% | 67% | 70% | 70% | 65% | 82% | |
| 72.7% | 76% | 75% | 71% | 73% | 68% | 73% | |
| 68.2% | 66% | 64% | 67% | 73% | 70% | 69% |