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 Israel. Source: Global Dialogues GD6 (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 63.1% | 4th 59.1% | 3rd 59.4% | 2nd 61.5% | 6th 56.9% | 5th 57.8% | |
| 80.2% | 91% | 78% | 78% | 79% | 85% | 70% | |
| 58.3% | 79% | 69% | 43% | 51% | 47% | 61% | |
| 46.2% | 51% | 39% | 41% | 48% | 48% | 50% | |
| 58.7% | 53% | 58% | 66% | 58% | 67% | 50% | |
| 56.2% | 65% | 50% | 45% | 61% | 61% | 55% | |
| 69.2% | 64% | 71% | 77% | 77% | 59% | 67% | |
| 59.5% | 58% | 61% | 62% | 63% | 54% | 59% | |
| 43.7% | 50% | 34% | 56% | 49% | 33% | 40% | |
| 59.8% | 58% | 58% | 60% | 63% | 58% | 62% | |
| 64.7% | 62% | 73% | 66% | 66% | 57% | 64% |