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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 2nd 84.0% | 17th 72.2% | 1st 86.5% | 3rd 82.3% | 7th 79.5% | 16th 72.7% | 3rd 82.3% | 15th 73.3% | 14th 75.0% | 11th 76.8% | 8th 79.3% | 9th 79.0% | 11th 76.8% | 21st 68.5% | 5th 81.0% | 20th 70.5% | 11th 76.8% | 19th 71.5% | 17th 72.2% | 6th 79.5% | 10th 77.5% | |
| 80.0% | 91% | 64% | 88% | 75% | 86% | 73% | 92% | 81% | 84% | 78% | 92% | 81% | 76% | 90% | 83% | 72% | 76% | 63% | 76% | 84% | 74% | |
| 76.8% | 78% | 78% | 85% | 78% | 96% | 69% | 81% | 69% | 78% | 75% | 75% | 78% | 78% | 78% | 92% | 69% | 75% | 69% | 70% | 78% | 64% | |
| 69.0% | 78% | 65% | 75% | 78% | 76% | 65% | 78% | 65% | 57% | 65% | 69% | 68% | 75% | 41% | 60% | 65% | 78% | 77% | 65% | 78% | 72% | |
| 82.2% | 89% | 82% | 98% | 98% | 60% | 84% | 78% | 78% | 81% | 89% | 81% | 89% | 78% | 65% | 89% | 76% | 78% | 77% | 78% | 78% | 100% |