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 GD2 (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 | 4th 72.0% | 7th 71.3% | 8th 70.0% | 11th 67.3% | 1st 77.7% | 21st 59.0% | 19th 61.0% | 14th 66.7% | 17th 63.3% | 12th 67.0% | 10th 68.3% | 13th 67.0% | 15th 65.7% | 9th 69.7% | 2nd 72.3% | 4th 72.0% | 18th 62.3% | 2nd 72.3% | 15th 65.7% | 19th 61.0% | 6th 71.7% | |
| 72.3% | 76% | 76% | 77% | 77% | 77% | 69% | 64% | 69% | 69% | 68% | 78% | 69% | 69% | 78% | 77% | 72% | 69% | 77% | 69% | 69% | 69% | |
| 42.2% | 46% | 50% | 49% | 50% | 61% | 30% | 35% | 36% | 33% | 43% | 36% | 43% | 34% | 36% | 54% | 50% | 39% | 43% | 38% | 30% | 50% | |
| 88.9% | 94% | 88% | 84% | 75% | 95% | 78% | 84% | 95% | 88% | 90% | 91% | 89% | 94% | 95% | 86% | 94% | 79% | 97% | 90% | 84% | 96% |