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 Japan. 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 71.0% | 9th 68.3% | 8th 68.8% | 4th 70.5% | 10th 64.3% | 11th 63.2% | 5th 69.5% | 13th 54.0% | 5th 69.5% | 12th 58.8% | 2nd 72.5% | 7th 69.0% | 1st 76.8% | |
| 66.1% | 69% | 66% | 66% | 69% | 62% | 74% | 71% | 55% | 65% | 62% | 67% | 66% | 67% | |
| 65.4% | 74% | 68% | 62% | 63% | 63% | 62% | 71% | 54% | 71% | 46% | 70% | 71% | 75% | |
| 49.7% | 48% | 48% | 56% | 63% | 46% | 46% | 45% | 38% | 48% | 36% | 56% | 48% | 68% | |
| 88.4% | 93% | 91% | 91% | 87% | 86% | 71% | 91% | 69% | 94% | 91% | 97% | 91% | 97% |