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 | 2nd 65.3% | 3rd 65.0% | 5th 61.9% | 1st 66.8% | 6th 58.5% | 4th 64.8% | |
| 79.3% | 75% | 90% | 72% | 79% | 81% | 79% | |
| 55.0% | 59% | 61% | 49% | 61% | 52% | 48% | |
| 50.8% | 47% | 45% | 54% | 49% | 54% | 56% | |
| 57.8% | 53% | 55% | 53% | 68% | 55% | 63% | |
| 58.3% | 70% | 58% | 57% | 61% | 40% | 64% | |
| 72.7% | 77% | 66% | 74% | 75% | 67% | 77% | |
| 61.2% | 67% | 66% | 62% | 67% | 39% | 66% | |
| 63.3% | 67% | 52% | 62% | 71% | 58% | 70% | |
| 63.7% | 59% | 77% | 66% | 63% | 60% | 57% | |
| 75.0% | 79% | 80% | 70% | 74% | 79% | 68% |