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 Kazakhstan. 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 | 4th 68.3% | 6th 52.6% | 3rd 69.1% | 2nd 70.9% | 5th 63.8% | 1st 71.0% | |
| 86.2% | 93% | 86% | 82% | 90% | 80% | 86% | |
| 66.5% | 67% | 75% | 67% | 69% | 57% | 64% | |
| 50.2% | 51% | 0% | 71% | 57% | 56% | 66% | |
| 87.5% | 95% | 92% | 81% | 92% | 72% | 93% | |
| 49.8% | 57% | 38% | 42% | 49% | 63% | 50% | |
| 66.5% | 64% | 59% | 73% | 71% | 63% | 69% | |
| 40.3% | 44% | 40% | 43% | 44% | 37% | 34% | |
| 78.8% | 67% | 86% | 82% | 82% | 73% | 83% | |
| 63.7% | 62% | 50% | 69% | 69% | 56% | 76% | |
| 70.0% | 83% | 0% | 81% | 86% | 81% | 89% |