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 Kazakhstan. 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 | 5th 65.7% | 6th 62.4% | 4th 68.2% | 2nd 71.6% | 3rd 69.6% | 1st 77.2% | |
| 68.7% | 56% | 60% | 81% | 64% | 67% | 84% | |
| 77.8% | 72% | 74% | 77% | 80% | 84% | 80% | |
| 59.3% | 64% | 61% | 57% | 57% | 60% | 57% | |
| 73.5% | 78% | 60% | 74% | 77% | 65% | 87% | |
| 73.0% | 69% | 74% | 69% | 74% | 76% | 76% | |
| 78.3% | 67% | 74% | 79% | 83% | 77% | 90% | |
| 49.2% | 44% | 37% | 49% | 58% | 52% | 55% | |
| 71.3% | 75% | 53% | 66% | 79% | 69% | 86% | |
| 69.7% | 71% | 59% | 67% | 71% | 74% | 76% | |
| 70.3% | 61% | 72% | 63% | 73% | 72% | 81% |