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 | 1st 64.6% | 4th 61.7% | 6th 56.3% | 2nd 63.5% | 5th 60.4% | 3rd 63.3% | |
| 59.8% | 54% | 67% | 57% | 53% | 74% | 54% | |
| 56.7% | 53% | 58% | 53% | 63% | 52% | 61% | |
| 59.2% | 67% | 43% | 55% | 68% | 65% | 57% | |
| 75.3% | 78% | 69% | 68% | 72% | 93% | 72% | |
| 37.8% | 34% | 62% | 34% | 39% | 25% | 33% | |
| 68.7% | 66% | 71% | 62% | 76% | 64% | 73% | |
| 59.7% | 66% | 69% | 56% | 61% | 43% | 63% | |
| 79.8% | 78% | 77% | 76% | 78% | 92% | 78% | |
| 60.2% | 75% | 47% | 64% | 35% | 80% | ||
| 59.8% | 75% | 54% | 46% | 61% | 61% | 62% |