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 | 8th 82.0% | 5th 82.8% | 3rd 84.0% | 2nd 84.3% | 14th 78.3% | 15th 78.0% | 19th 77.5% | 18th 77.8% | 12th 79.3% | 9th 81.8% | 6th 82.5% | 20th 75.3% | 4th 83.2% | 11th 80.8% | 7th 82.3% | 12th 79.3% | 17th 78.0% | 10th 81.5% | 1st 84.8% | 21st 72.3% | 15th 78.0% | |
| 61.4% | 65% | 59% | 54% | 61% | 67% | 54% | 51% | 60% | 58% | 59% | 65% | 67% | 66% | 67% | 68% | 61% | 55% | 72% | 63% | 59% | 59% | |
| 87.9% | 86% | 86% | 93% | 80% | 90% | 87% | 90% | 91% | 89% | 93% | 90% | 76% | 97% | 87% | 93% | 93% | 83% | 85% | 94% | 72% | 90% | |
| 85.1% | 86% | 90% | 92% | 99% | 84% | 82% | 85% | 82% | 86% | 84% | 84% | 73% | 84% | 90% | 83% | 85% | 84% | 79% | 89% | 83% | 83% | |
| 86.2% | 91% | 96% | 97% | 97% | 72% | 89% | 84% | 78% | 84% | 91% | 91% | 85% | 86% | 79% | 85% | 78% | 90% | 90% | 93% | 75% | 80% |