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 Philippines. 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 | 3rd 77.7% | 2nd 78.0% | 1st 78.3% | 8th 73.0% | 5th 73.7% | 10th 71.7% | 9th 72.0% | 11th 71.3% | 12th 71.0% | 13th 70.0% | 7th 73.3% | 5th 73.7% | 4th 74.5% | |
| 76.5% | 81% | 84% | 84% | 62% | 84% | 75% | 73% | 73% | 75% | 77% | 73% | |||
| 68.6% | 75% | 76% | 74% | 75% | 68% | 64% | 64% | 62% | 62% | 61% | 64% | 71% | 76% | |
| 76.7% | 77% | 74% | 77% | 82% | 69% | 76% | 79% | 79% | 76% | 79% | 79% | 77% | 73% |