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 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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 12th 77.3% | 4th 80.7% | 7th 80.0% | 8th 79.7% | 4th 80.7% | 21st 68.7% | 20th 70.3% | 19th 71.7% | 11th 77.7% | 3rd 81.7% | 14th 76.3% | 10th 78.0% | 15th 75.3% | 1st 83.0% | 2nd 82.0% | 6th 80.3% | 16th 74.3% | 12th 77.3% | 9th 79.0% | 17th 72.3% | 17th 72.3% | |
| 82.9% | 79% | 84% | 82% | 82% | 82% | 81% | 76% | 88% | 88% | 84% | 86% | 83% | 77% | 90% | 88% | 82% | 83% | 90% | 88% | 78% | 69% | |
| 74.0% | 78% | 83% | 84% | 85% | 76% | 55% | 63% | 54% | 75% | 84% | 74% | 75% | 71% | 78% | 83% | 83% | 71% | 64% | 71% | 69% | 79% | |
| 74.3% | 75% | 75% | 74% | 72% | 84% | 70% | 72% | 73% | 70% | 77% | 69% | 76% | 78% | 81% | 75% | 76% | 69% | 78% | 78% | 70% | 69% |