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 More concerned than excited. 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 | 2nd 74.8% | 6th 71.5% | 1st 76.8% | 13th 60.8% | 7th 71.5% | 5th 72.8% | 11th 66.5% | 12th 64.5% | 4th 73.0% | 8th 70.3% | 3rd 73.8% | 10th 68.0% | 9th 69.8% | |
| 61.0% | 61% | 57% | 67% | 77% | 56% | 62% | 51% | 63% | 62% | 63% | 69% | 52% | 53% | |
| 84.8% | 94% | 82% | 81% | 66% | 84% | 91% | 84% | 80% | 91% | 88% | 87% | 85% | 89% | |
| 55.2% | 61% | 67% | 76% | 42% | 59% | 55% | 54% | 50% | 52% | 42% | 52% | 54% | 54% | |
| 80.2% | 83% | 80% | 83% | 58% | 87% | 83% | 77% | 65% | 87% | 88% | 87% | 81% | 83% |