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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 12th 75.7% | 4th 81.0% | 5th 80.3% | 5th 80.3% | 3rd 81.7% | 17th 72.0% | 20th 71.0% | 18th 71.7% | 10th 77.7% | 8th 78.7% | 13th 75.3% | 8th 78.7% | 14th 74.0% | 1st 83.0% | 2nd 82.7% | 5th 80.3% | 15th 73.3% | 19th 71.7% | 11th 76.7% | 16th 72.3% | |
| 83.9% | 76% | 84% | 82% | 85% | 86% | 81% | 76% | 88% | 88% | 81% | 86% | 83% | 82% | 90% | 90% | 85% | 83% | 88% | 83% | 81% | |
| 72.4% | 78% | 84% | 84% | 84% | 78% | 57% | 60% | 55% | 75% | 78% | 74% | 75% | 62% | 78% | 84% | 83% | 69% | 63% | 69% | 58% | |
| 74.4% | 73% | 75% | 75% | 72% | 81% | 78% | 77% | 72% | 70% | 77% | 66% | 78% | 78% | 81% | 74% | 73% | 68% | 64% | 78% | 78% |