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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 4th 78.0% | 2nd 78.5% | 1st 80.0% | 10th 75.3% | 8th 77.0% | 19th 68.0% | 21st 64.5% | 12th 73.3% | 13th 72.5% | 6th 77.5% | 5th 77.8% | 20th 66.3% | 16th 70.5% | 7th 77.3% | 2nd 78.5% | 8th 77.0% | 14th 72.0% | 11th 73.8% | 15th 72.0% | 18th 68.3% | 17th 69.5% | |
| 53.2% | 57% | 53% | 51% | 51% | 54% | 54% | 51% | 59% | 48% | 54% | 54% | 59% | 60% | 60% | 46% | 52% | 54% | 51% | 56% | 51% | 43% | |
| 85.6% | 83% | 87% | 94% | 90% | 80% | 85% | 87% | 87% | 85% | 90% | 92% | 81% | 87% | 89% | 90% | 89% | 83% | 81% | 86% | 75% | 76% | |
| 73.0% | 78% | 83% | 83% | 83% | 82% | 58% | 61% | 54% | 74% | 78% | 73% | 58% | 61% | 74% | 84% | 85% | 68% | 73% | 69% | 73% | 82% | |
| 82.9% | 94% | 91% | 92% | 77% | 92% | 75% | 59% | 93% | 83% | 88% | 92% | 67% | 74% | 86% | 94% | 82% | 83% | 90% | 77% | 74% | 77% |