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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 7th 81.3% | 4th 82.8% | 5th 82.5% | 2nd 84.3% | 20th 75.8% | 15th 78.0% | 16th 77.5% | 17th 76.8% | 11th 80.3% | 9th 81.2% | 10th 81.0% | 21st 72.3% | 6th 81.5% | 12th 79.5% | 7th 81.3% | 13th 78.8% | 18th 76.3% | 18th 76.3% | 1st 84.5% | 3rd 83.3% | 14th 78.3% | |
| 61.7% | 65% | 59% | 54% | 61% | 67% | 54% | 51% | 63% | 55% | 58% | 64% | 67% | 67% | 67% | 66% | 60% | 59% | 51% | 63% | 72% | 72% | |
| 87.7% | 80% | 86% | 93% | 80% | 89% | 87% | 90% | 86% | 97% | 97% | 86% | 76% | 97% | 84% | 91% | 86% | 86% | 83% | 94% | 96% | 77% | |
| 83.2% | 86% | 90% | 86% | 99% | 83% | 82% | 85% | 81% | 85% | 84% | 83% | 61% | 79% | 83% | 85% | 86% | 77% | 81% | 88% | 85% | 79% | |
| 86.1% | 94% | 96% | 97% | 97% | 64% | 89% | 84% | 77% | 84% | 86% | 91% | 85% | 83% | 84% | 83% | 83% | 83% | 90% | 93% | 80% | 85% |