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 Pakistan. 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 | 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 81.0% | 2nd 82.0% | 8th 79.3% | 1st 82.3% | 13th 69.3% | 12th 72.0% | 6th 79.7% | 6th 79.7% | 9th 78.3% | 11th 77.7% | 2nd 82.0% | 10th 78.3% | 5th 80.7% | |
| 85.0% | 84% | 88% | 82% | 82% | 81% | 76% | 88% | 84% | 90% | 82% | 90% | 88% | 90% | |
| 76.2% | 84% | 84% | 88% | 84% | 57% | 63% | 74% | 78% | 74% | 75% | 75% | 69% | 85% | |
| 74.8% | 75% | 74% | 68% | 81% | 70% | 77% | 77% | 77% | 71% | 76% | 81% | 78% | 67% |