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 | 6th 83.3% | 17th 74.0% | 2nd 86.5% | 5th 83.8% | 3rd 85.2% | 16th 74.5% | 7th 82.0% | 18th 73.3% | 11th 77.0% | 14th 75.0% | 4th 84.3% | 8th 79.0% | 13th 75.3% | 21st 67.5% | 10th 77.8% | 20th 70.5% | 15th 74.5% | 12th 76.5% | 19th 72.2% | 9th 78.5% | 1st 89.0% | |
| 80.6% | 91% | 64% | 88% | 81% | 86% | 73% | 91% | 81% | 84% | 78% | 89% | 81% | 80% | 90% | 84% | 72% | 72% | 75% | 76% | 83% | 74% | |
| 77.3% | 78% | 78% | 85% | 78% | 96% | 76% | 81% | 69% | 78% | 75% | 73% | 78% | 78% | 69% | 78% | 69% | 70% | 77% | 75% | 78% | 84% | |
| 70.0% | 75% | 65% | 75% | 78% | 77% | 65% | 78% | 65% | 65% | 65% | 75% | 68% | 65% | 42% | 60% | 65% | 78% | 77% | 60% | 75% | 98% | |
| 84.3% | 89% | 89% | 98% | 98% | 82% | 84% | 78% | 78% | 81% | 82% | 100% | 89% | 78% | 69% | 89% | 76% | 78% | 77% | 78% | 78% | 100% |