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 Indonesia. 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 73.2% | 1st 75.3% | 6th 61.2% | 4th 67.8% | 5th 66.8% | 3rd 68.0% | |
| 68.7% | 74% | 68% | 56% | 68% | 73% | 73% | |
| 62.8% | 61% | 77% | 46% | 60% | 72% | 61% | |
| 70.0% | 67% | 75% | 60% | 73% | 71% | 74% | |
| 52.8% | 59% | 75% | 35% | 65% | 29% | 54% | |
| 74.2% | 76% | 68% | 75% | 77% | 73% | 76% | |
| 68.5% | 77% | 82% | 64% | 65% | 56% | 67% | |
| 87.3% | 96% | 92% | 73% | 79% | 92% | 92% | |
| 69.8% | 77% | 79% | 64% | 64% | 66% | 69% | |
| 67.0% | 69% | 73% | 69% | 63% | 74% | 54% | |
| 66.0% | 76% | 64% | 70% | 64% | 62% | 60% |