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 46-55. 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 | 7th 79.8% | 13th 74.0% | 11th 75.5% | 9th 77.8% | 5th 80.8% | 8th 78.5% | 11th 75.5% | 10th 76.8% | 2nd 81.8% | 5th 80.8% | 3rd 81.5% | 1st 82.2% | 4th 81.3% | |
| 76.5% | 78% | 68% | 65% | 78% | 71% | 77% | 73% | 69% | 82% | 83% | 87% | 84% | 80% | |
| 76.5% | 75% | 69% | 73% | 73% | 82% | 81% | 70% | 78% | 83% | 74% | 79% | 77% | 81% | |
| 76.3% | 80% | 75% | 80% | 72% | 80% | 74% | 75% | 79% | 75% | 72% | 72% | 78% | 80% | |
| 86.3% | 86% | 84% | 84% | 88% | 90% | 82% | 84% | 81% | 87% | 94% | 88% | 90% | 84% |