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 | 9th 78.3% | 3rd 81.0% | 2nd 81.3% | 12th 78.0% | 4th 80.7% | 20th 70.3% | 21st 69.3% | 18th 73.3% | 14th 77.7% | 7th 79.7% | 16th 76.3% | 11th 78.3% | 8th 78.7% | 4th 80.7% | 1st 85.3% | 9th 78.3% | 17th 73.7% | 19th 70.7% | 15th 76.7% | 4th 80.7% | 12th 78.0% | |
| 83.6% | 84% | 84% | 88% | 82% | 86% | 81% | 76% | 93% | 88% | 84% | 82% | 84% | 80% | 86% | 86% | 81% | 82% | 77% | 83% | 88% | 81% | |
| 74.4% | 76% | 84% | 84% | 84% | 83% | 60% | 60% | 55% | 75% | 78% | 74% | 75% | 75% | 75% | 85% | 80% | 70% | 62% | 69% | 81% | 78% | |
| 74.4% | 75% | 75% | 72% | 68% | 73% | 70% | 72% | 72% | 70% | 77% | 73% | 76% | 81% | 81% | 85% | 74% | 69% | 73% | 78% | 73% | 75% |