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 China. 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 | 1st 78.7% | 3rd 76.0% | 2nd 78.2% | 5th 73.7% | 6th 68.8% | 4th 74.9% | |
| 77.8% | 79% | 68% | 74% | 70% | 83% | 93% | |
| 75.7% | 79% | 75% | 85% | 78% | 62% | 75% | |
| 62.2% | 67% | 60% | 71% | 61% | 57% | 57% | |
| 78.0% | 89% | 89% | 66% | 89% | 67% | 68% | |
| 80.2% | 79% | 74% | 82% | 80% | 81% | 85% | |
| 70.5% | 81% | 81% | 73% | 71% | 52% | 65% | |
| 76.7% | 77% | 78% | 92% | 67% | 67% | 79% | |
| 77.7% | 84% | 85% | 72% | 76% | 72% | 77% | |
| 77.8% | 74% | 76% | 88% | 73% | 80% | 76% | |
| 74.0% | 78% | 74% | 79% | 72% | 67% | 74% |