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 | 6th 72.7% | 1st 76.3% | 10th 71.3% | 3rd 75.0% | 13th 68.0% | 9th 72.0% | 12th 69.0% | 11th 70.7% | 3rd 75.0% | 6th 72.7% | 2nd 75.3% | 5th 73.0% | 8th 72.3% | |
| 69.5% | 67% | 73% | 73% | 73% | 57% | 73% | 72% | 76% | 65% | 69% | 73% | 62% | 70% | |
| 61.3% | 61% | 71% | 56% | 65% | 63% | 58% | 54% | 53% | 71% | 56% | 56% | 68% | 65% | |
| 86.9% | 90% | 85% | 85% | 87% | 84% | 85% | 81% | 83% | 89% | 93% | 97% | 89% | 82% |