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 GD4 (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 | 3rd 70.1% | 1st 73.0% | 6th 60.6% | 5th 68.5% | 2nd 71.1% | 4th 69.9% | |
| 71.8% | 66% | 69% | 78% | 74% | 66% | 78% | |
| 68.5% | 73% | 70% | 56% | 70% | 72% | 71% | |
| 79.8% | 81% | 80% | 83% | 82% | 76% | 78% | |
| 70.8% | 61% | 77% | 62% | 66% | 80% | 80% | |
| 73.7% | 75% | 72% | 72% | 73% | 79% | 71% | |
| 71.8% | 77% | 79% | 68% | 67% | 71% | 70% | |
| 42.2% | 38% | 49% | 36% | 41% | 44% | 45% | |
| 69.3% | 81% | 79% | 48% | 73% | 76% | 60% | |
| 64.6% | 72% | 72% | 45% | 64% | 66% | 70% | |
| 76.3% | 80% | 85% | 59% | 76% | 82% | 76% |