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 83.3% | 16th 74.0% | 1st 86.5% | 7th 78.8% | 13th 75.5% | 19th 71.0% | 4th 79.3% | 14th 75.5% | 15th 75.3% | 10th 76.8% | 4th 79.3% | 6th 79.0% | 10th 76.8% | 21st 67.0% | 12th 76.5% | 17th 73.8% | 18th 71.8% | 20th 70.5% | 8th 78.5% | 3rd 79.5% | 9th 77.5% | |
| 79.2% | 91% | 64% | 88% | 81% | 81% | 73% | 80% | 90% | 84% | 78% | 92% | 81% | 83% | 82% | 79% | 72% | 69% | 67% | 90% | 84% | 54% | |
| 76.0% | 78% | 78% | 85% | 78% | 75% | 69% | 81% | 69% | 78% | 75% | 59% | 78% | 78% | 78% | 78% | 82% | 77% | 77% | 68% | 78% | 78% | |
| 68.3% | 75% | 65% | 75% | 78% | 77% | 65% | 78% | 65% | 55% | 65% | 84% | 68% | 68% | 39% | 60% | 65% | 65% | 54% | 78% | 78% | 78% | |
| 82.3% | 89% | 89% | 98% | 78% | 69% | 77% | 78% | 78% | 84% | 89% | 82% | 89% | 78% | 69% | 89% | 76% | 76% | 84% | 78% | 78% | 100% |