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 Pakistan. 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 79.5% | 4th 78.5% | 1st 80.0% | 11th 74.5% | 4th 78.5% | 18th 66.8% | 21st 64.5% | 16th 68.8% | 12th 72.3% | 8th 76.8% | 7th 77.8% | 18th 66.8% | 17th 68.0% | 9th 76.3% | 3rd 79.3% | 6th 78.3% | 14th 71.5% | 15th 69.3% | 10th 75.5% | 20th 66.0% | 13th 72.0% | |
| 53.4% | 60% | 53% | 51% | 51% | 54% | 54% | 53% | 59% | 48% | 54% | 54% | 55% | 53% | 60% | 55% | 51% | 49% | 43% | 56% | 51% | 58% | |
| 86.8% | 90% | 87% | 94% | 90% | 89% | 80% | 82% | 89% | 85% | 88% | 92% | 85% | 86% | 85% | 89% | 89% | 83% | 83% | 86% | 80% | 90% | |
| 72.2% | 78% | 83% | 83% | 83% | 79% | 58% | 61% | 53% | 73% | 77% | 73% | 55% | 61% | 74% | 85% | 84% | 77% | 61% | 79% | 68% | 71% | |
| 81.0% | 90% | 91% | 92% | 74% | 92% | 75% | 62% | 74% | 83% | 88% | 92% | 72% | 72% | 86% | 88% | 89% | 77% | 90% | 81% | 65% | 69% |