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 Germany. 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 | 12th 62.0% | 8th 64.3% | 5th 67.0% | 7th 64.7% | 13th 56.7% | 6th 66.0% | 9th 64.0% | 11th 62.7% | 3rd 71.0% | 9th 64.0% | 4th 70.3% | 1st 72.7% | 2nd 71.3% | |
| 63.6% | 51% | 60% | 73% | 70% | 53% | 65% | 64% | 75% | 60% | 62% | 65% | 64% | 65% | |
| 57.7% | 58% | 61% | 56% | 59% | 49% | 56% | 52% | 47% | 63% | 54% | 58% | 78% | 59% | |
| 76.4% | 77% | 72% | 72% | 65% | 68% | 77% | 76% | 66% | 90% | 76% | 88% | 76% | 90% |