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 United Kingdom. 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 75.8% | 11th 71.2% | 7th 73.8% | 2nd 77.0% | 9th 72.3% | 10th 71.3% | 12th 71.0% | 13th 69.5% | 5th 74.8% | 2nd 77.0% | 6th 74.0% | 8th 73.3% | 1st 78.3% | |
| 67.9% | 70% | 60% | 60% | 70% | 66% | 68% | 69% | 60% | 71% | 76% | 74% | 66% | 73% | |
| 74.1% | 82% | 70% | 72% | 75% | 74% | 66% | 66% | 68% | 83% | 81% | 72% | 76% | 78% | |
| 70.7% | 74% | 72% | 79% | 74% | 72% | 69% | 66% | 68% | 64% | 70% | 63% | 72% | 76% | |
| 82.4% | 77% | 83% | 84% | 89% | 77% | 82% | 83% | 82% | 81% | 81% | 87% | 79% | 86% |