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 Australia. Source: Global Dialogues GD6 (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 66.6% | 1st 68.4% | 5th 63.1% | 2nd 67.3% | 6th 59.8% | 4th 65.3% | |
| 76.0% | 75% | 89% | 75% | 82% | 62% | 73% | |
| 75.3% | 88% | 88% | 62% | 68% | 66% | 80% | |
| 80.0% | 87% | 73% | 79% | 81% | 77% | 83% | |
| 60.0% | 58% | 57% | 66% | 59% | 66% | 54% | |
| 57.8% | 71% | 54% | 41% | 61% | 57% | 63% | |
| 50.5% | 47% | 58% | 64% | 51% | 36% | 47% | |
| 55.8% | 58% | 57% | 52% | 59% | 53% | ||
| 66.5% | 65% | 73% | 67% | 67% | 56% | 71% | |
| 62.5% | 66% | 63% | 55% | 63% | 60% | 68% | |
| 64.5% | 51% | 72% | 70% | 74% | 59% | 61% |