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 Kazakhstan. 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 | 7th 72.0% | 5th 75.0% | 2nd 76.7% | 1st 77.7% | 13th 65.7% | 3rd 76.0% | 4th 75.3% | 9th 71.0% | 11th 69.3% | 12th 68.3% | 10th 69.7% | 5th 75.0% | 8th 71.7% | |
| 73.8% | 69% | 65% | 70% | 83% | 61% | 83% | 83% | 78% | 69% | 78% | 78% | 76% | 67% | |
| 56.0% | 56% | 66% | 65% | 58% | 52% | 56% | 53% | 54% | 56% | 41% | 49% | 63% | 59% | |
| 87.8% | 91% | 94% | 95% | 92% | 84% | 89% | 90% | 81% | 83% | 86% | 82% | 86% | 89% |