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 84.0% | 1st 86.5% | 3rd 83.8% | 4th 83.5% | 16th 73.3% | 17th 72.7% | 20th 71.8% | 15th 74.0% | 14th 76.8% | 8th 81.5% | 12th 78.8% | 10th 79.3% | 9th 81.0% | 19th 72.2% | 13th 77.0% | 6th 82.3% | 21st 69.8% | 17th 72.7% | 10th 79.3% | 4th 83.5% | 7th 82.0% | |
| 78.6% | 91% | 88% | 81% | 83% | 79% | 73% | 75% | 84% | 78% | 81% | 83% | 90% | 83% | 79% | 76% | 92% | 60% | 74% | 83% | 54% | 64% | |
| 76.8% | 78% | 85% | 78% | 78% | 77% | 69% | 69% | 78% | 75% | 78% | 78% | 69% | 92% | 69% | 75% | 78% | 77% | 68% | 78% | 82% | 82% | |
| 72.1% | 78% | 75% | 78% | 75% | 65% | 65% | 65% | 65% | 65% | 78% | 65% | 60% | 60% | 65% | 75% | 75% | 64% | 65% | 78% | 98% | 100% | |
| 85.9% | 89% | 98% | 98% | 98% | 72% | 84% | 78% | 69% | 89% | 89% | 89% | 98% | 89% | 76% | 82% | 84% | 78% | 84% | 78% | 100% | 82% |