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 France. 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 | 11th 68.7% | 3rd 76.3% | 1st 77.0% | 2nd 76.7% | 12th 68.0% | 7th 73.0% | 13th 63.5% | 10th 70.7% | 8th 72.3% | 9th 71.7% | 4th 74.0% | 4th 74.0% | 6th 73.5% | |
| 68.3% | 59% | 73% | 73% | 73% | 57% | 73% | 73% | 76% | 59% | 69% | 73% | 62% | ||
| 62.7% | 61% | 71% | 73% | 65% | 63% | 61% | 54% | 53% | 69% | 53% | 56% | 71% | 65% | |
| 87.2% | 86% | 85% | 85% | 92% | 84% | 85% | 83% | 89% | 93% | 93% | 89% | 82% |