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 Morocco. Source: Global Dialogues GD1 (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 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o Mini | Qwen3 30b A3B Instruct 2507 | Qwen3 Next 80b A3B Instruct | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 4th 82.3% | 6th 78.3% | 2nd 82.8% | 10th 75.0% | 11th 74.3% | 12th 71.5% | 9th 77.3% | 3rd 82.5% | 6th 78.3% | 13th 70.8% | 6th 78.3% | 1st 83.0% | 5th 81.0% | |
| 71.3% | 70% | 62% | 80% | 67% | 52% | 60% | 70% | 79% | 80% | 70% | 83% | 75% | 79% | |
| 79.2% | 82% | 84% | 84% | 83% | 77% | 82% | 74% | 84% | 77% | 54% | 77% | 82% | 89% | |
| 86.9% | 97% | 89% | 89% | 97% | 91% | 67% | 88% | 88% | 78% | 81% | 84% | 97% | 84% | |
| 74.9% | 80% | 78% | 78% | 53% | 77% | 77% | 77% | 79% | 78% | 78% | 69% | 78% | 72% |