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 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 | 3rd 78.5% | 2nd 80.0% | 8th 74.5% | 6th 77.3% | 11th 68.0% | 13th 64.5% | 9th 73.8% | 5th 77.5% | 4th 78.5% | 12th 65.5% | 7th 76.3% | 10th 71.3% | 1st 80.3% | |
| 53.2% | 53% | 51% | 51% | 55% | 54% | 51% | 45% | 58% | 55% | 55% | 60% | 52% | 51% | |
| 88.6% | 87% | 94% | 90% | 80% | 85% | 87% | 94% | 87% | 94% | 85% | 90% | 87% | 92% | |
| 73.5% | 83% | 83% | 83% | 82% | 58% | 61% | 73% | 77% | 73% | 55% | 74% | 69% | 85% | |
| 81.8% | 91% | 92% | 74% | 92% | 75% | 59% | 83% | 88% | 92% | 67% | 81% | 77% | 93% |