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 Chile. 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 | 11th 64.7% | 6th 69.0% | 7th 66.7% | 1st 75.7% | 13th 63.3% | 7th 66.7% | 9th 66.3% | 10th 65.7% | 3rd 71.0% | 12th 63.7% | 3rd 71.0% | 2nd 72.0% | 5th 69.7% | |
| 72.0% | 64% | 67% | 71% | 93% | 67% | 75% | 71% | 79% | 73% | 66% | 73% | 67% | 70% | |
| 57.5% | 57% | 72% | 56% | 63% | 53% | 53% | 53% | 55% | 55% | 51% | 53% | 68% | 59% | |
| 74.8% | 73% | 68% | 73% | 71% | 70% | 72% | 75% | 63% | 85% | 74% | 87% | 81% | 80% |