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 Russian Federation. Source: Global Dialogues GD5 (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 74.4% | 4th 73.8% | 5th 68.1% | 3rd 73.9% | 6th 65.3% | 1st 75.8% | |
| 71.8% | 68% | 69% | 62% | 72% | 83% | 77% | |
| 72.0% | 78% | 78% | 78% | 77% | 52% | 69% | |
| 52.7% | 50% | 50% | 61% | 53% | 38% | 64% | |
| 69.8% | 79% | 84% | 64% | 76% | 42% | 74% | |
| 66.2% | 71% | 59% | 64% | 67% | 63% | 73% | |
| 83.7% | 82% | 93% | 78% | 85% | 83% | 81% | |
| 86.7% | 81% | 85% | 74% | 90% | 95% | 95% | |
| 69.2% | 72% | 72% | 74% | 68% | 55% | 74% | |
| 72.0% | 76% | 70% | 60% | 73% | 80% | 73% | |
| 74.8% | 87% | 78% | 66% | 78% | 62% | 78% |