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 | 6th 78.0% | 5th 78.5% | 1st 80.8% | 9th 76.0% | 10th 75.3% | 18th 66.8% | 20th 65.3% | 11th 74.3% | 13th 72.8% | 7th 77.3% | 4th 78.8% | 21st 60.0% | 15th 72.0% | 7th 77.3% | 2nd 79.5% | 3rd 79.3% | 17th 68.5% | 16th 69.0% | 14th 72.5% | 19th 66.3% | 12th 74.0% | |
| 54.0% | 57% | 53% | 54% | 51% | 55% | 54% | 53% | 59% | 48% | 55% | 55% | 55% | 60% | 59% | 56% | 55% | 44% | 47% | 56% | 48% | 60% | |
| 86.9% | 89% | 87% | 94% | 94% | 80% | 80% | 88% | 89% | 85% | 88% | 94% | 81% | 85% | 90% | 89% | 91% | 83% | 78% | 86% | 85% | 88% | |
| 73.5% | 78% | 83% | 83% | 85% | 76% | 58% | 61% | 72% | 75% | 78% | 73% | 55% | 71% | 74% | 85% | 85% | 73% | 61% | 71% | 69% | 77% | |
| 79.3% | 88% | 91% | 92% | 74% | 90% | 75% | 59% | 77% | 83% | 88% | 93% | 49% | 72% | 86% | 88% | 86% | 74% | 90% | 77% | 63% | 71% |