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 Egypt. 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 3.7 Sonnet | Claude Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT 5 | GPT 5.1 | GPT OSS 120b | GPT OSS 20b | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | Grok 4 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 84.0% | 1st 86.5% | 5th 82.3% | 4th 83.5% | 17th 74.3% | 19th 72.7% | 18th 73.3% | 15th 75.3% | 13th 77.0% | 7th 81.5% | 14th 76.0% | 21st 66.3% | 11th 78.8% | 16th 74.5% | 2nd 84.5% | 7th 81.5% | 20th 68.5% | 10th 79.3% | 9th 79.5% | 11th 78.8% | 6th 82.0% | |
| 80.2% | 91% | 88% | 75% | 83% | 79% | 73% | 81% | 84% | 79% | 91% | 83% | 90% | 74% | 88% | 87% | 81% | 69% | 86% | 84% | 55% | 64% | |
| 75.8% | 78% | 85% | 78% | 78% | 77% | 69% | 69% | 78% | 75% | 78% | 78% | 64% | 92% | 69% | 78% | 79% | 67% | 75% | 78% | 82% | 64% | |
| 69.9% | 78% | 75% | 78% | 75% | 76% | 65% | 65% | 55% | 65% | 68% | 65% | 42% | 60% | 65% | 75% | 72% | 60% | 72% | 78% | 78% | 100% | |
| 86.5% | 89% | 98% | 98% | 98% | 65% | 84% | 78% | 84% | 89% | 89% | 78% | 69% | 89% | 76% | 98% | 94% | 78% | 84% | 78% | 100% | 100% |