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 Turkey. 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 | 6th 78.8% | 4th 80.0% | 8th 77.7% | 10th 74.5% | 13th 67.8% | 12th 73.8% | 9th 76.0% | 7th 77.8% | 1st 81.0% | 11th 74.3% | 3rd 80.5% | 5th 79.0% | 2nd 80.8% | |
| 59.9% | 59% | 52% | 58% | 59% | 45% | 47% | 54% | 57% | 74% | 62% | 77% | 64% | 71% | |
| 80.5% | 76% | 78% | 78% | 80% | 73% | 78% | 78% | 80% | 78% | 80% | 80% | 94% | 94% | |
| 85.9% | 95% | 95% | 95% | 79% | 73% | 91% | 95% | 95% | 83% | 75% | 83% | 79% | 79% | |
| 81.8% | 85% | 95% | 80% | 80% | 80% | 79% | 77% | 79% | 89% | 80% | 82% | 79% | 79% |