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 Indonesia. 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 | 3rd 76.0% | 6th 72.8% | 4th 74.8% | 2nd 77.3% | 13th 61.0% | 12th 64.3% | 8th 70.8% | 5th 73.8% | 7th 71.3% | 10th 68.3% | 9th 68.5% | 11th 67.0% | 1st 77.8% | |
| 72.2% | 81% | 65% | 65% | 75% | 53% | 64% | 78% | 78% | 77% | 80% | 76% | 66% | 81% | |
| 85.9% | 84% | 84% | 89% | 89% | 80% | 86% | 82% | 90% | 86% | 86% | 86% | 86% | 89% | |
| 61.8% | 69% | 70% | 73% | 73% | 56% | 54% | 61% | 63% | 56% | 51% | 52% | 55% | 70% | |
| 64.2% | 70% | 72% | 72% | 72% | 55% | 53% | 62% | 64% | 66% | 56% | 60% | 61% | 71% |