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 Korea South. Source: Global Dialogues GD2 (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 | 4th 76.3% | 1st 83.7% | 6th 72.0% | 2nd 81.3% | 5th 76.0% | 3rd 77.3% | |
| 80.7% | 77% | 93% | 70% | 77% | 90% | 77% | |
| 72.2% | 73% | 79% | 75% | 77% | 59% | 70% | |
| 80.5% | 79% | 79% | 71% | 90% | 79% | 85% |