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 | 6th 80.8% | 1st 86.5% | 4th 82.3% | 3rd 83.5% | 15th 74.5% | 19th 72.7% | 18th 73.3% | 20th 71.5% | 10th 77.0% | 5th 81.5% | 12th 76.0% | 21st 65.8% | 11th 76.3% | 14th 74.5% | 8th 79.0% | 9th 78.5% | 16th 74.3% | 13th 75.8% | 7th 79.5% | 16th 74.3% | 2nd 84.8% | |
| 78.0% | 91% | 88% | 75% | 83% | 86% | 73% | 81% | 79% | 79% | 91% | 83% | 90% | 64% | 79% | 82% | 82% | 76% | 66% | 84% | 49% | 58% | |
| 75.7% | 78% | 85% | 78% | 78% | 75% | 69% | 69% | 78% | 75% | 78% | 78% | 54% | 92% | 78% | 78% | 72% | 75% | 77% | 78% | 64% | 81% | |
| 70.7% | 65% | 75% | 78% | 75% | 77% | 65% | 65% | 57% | 65% | 68% | 65% | 41% | 60% | 65% | 78% | 78% | 68% | 77% | 78% | 84% | 100% | |
| 84.5% | 89% | 98% | 98% | 98% | 60% | 84% | 78% | 72% | 89% | 89% | 78% | 78% | 89% | 76% | 78% | 82% | 78% | 83% | 78% | 100% | 100% |