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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 13th 77.3% | 2nd 81.3% | 7th 79.7% | 3rd 81.0% | 9th 79.0% | 18th 72.7% | 21st 69.3% | 20th 71.3% | 14th 76.3% | 4th 80.0% | 14th 76.3% | 11th 78.7% | 17th 73.7% | 1st 83.0% | 7th 79.7% | 4th 80.0% | 16th 74.7% | 6th 80.0% | 11th 78.7% | 19th 71.7% | 9th 79.0% | |
| 83.1% | 80% | 84% | 82% | 82% | 86% | 81% | 76% | 88% | 85% | 84% | 86% | 83% | 78% | 93% | 84% | 86% | 86% | 83% | 88% | 72% | 79% | |
| 73.9% | 78% | 85% | 83% | 84% | 78% | 55% | 60% | 54% | 75% | 78% | 74% | 75% | 62% | 75% | 83% | 78% | 74% | 82% | 70% | 71% | 77% | |
| 74.9% | 74% | 75% | 74% | 77% | 73% | 82% | 72% | 72% | 69% | 78% | 69% | 78% | 81% | 81% | 72% | 76% | 64% | 75% | 78% | 72% | 81% |