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 | 2nd 86.3% | 1st 86.5% | 5th 82.3% | 4th 83.5% | 12th 76.8% | 18th 72.7% | 17th 73.3% | 16th 74.8% | 11th 77.0% | 6th 81.5% | 15th 76.0% | 21st 68.3% | 8th 78.8% | 19th 72.2% | 3rd 83.5% | 6th 81.5% | 20th 72.0% | 12th 76.8% | 10th 78.5% | 14th 76.5% | 9th 78.5% | |
| 80.2% | 91% | 88% | 75% | 83% | 86% | 73% | 81% | 84% | 79% | 91% | 83% | 90% | 83% | 79% | 83% | 81% | 72% | 72% | 83% | 64% | 64% | |
| 74.5% | 78% | 85% | 78% | 78% | 75% | 69% | 69% | 78% | 75% | 78% | 78% | 54% | 78% | 69% | 75% | 78% | 69% | 77% | 78% | 64% | 82% | |
| 70.6% | 78% | 75% | 78% | 75% | 77% | 65% | 65% | 65% | 65% | 68% | 65% | 60% | 65% | 65% | 78% | 78% | 63% | 77% | 75% | 78% | 68% | |
| 86.4% | 98% | 98% | 98% | 98% | 69% | 84% | 78% | 72% | 89% | 89% | 78% | 69% | 89% | 76% | 98% | 89% | 84% | 81% | 78% | 100% | 100% |