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 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 | 8th 66.0% | 4th 75.3% | 3rd 76.0% | 2nd 80.0% | 12th 63.0% | 1st 84.0% | 9th 65.7% | 5th 72.3% | 7th 69.3% | 13th 60.7% | 10th 65.0% | 11th 63.3% | 6th 69.7% | |
| 83.0% | 85% | 91% | 90% | 84% | 75% | 93% | 84% | 91% | 90% | 71% | 71% | 75% | 79% | |
| 63.5% | 67% | 78% | 69% | 56% | 61% | 59% | 62% | 60% | 59% | 55% | 57% | 64% | 79% | |
| 63.5% | 46% | 57% | 69% | 100% | 53% | 100% | 51% | 66% | 59% | 56% | 67% | 51% | 51% |