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 | 2nd 85.0% | 6th 82.8% | 4th 83.5% | 3rd 84.3% | 20th 72.0% | 18th 76.0% | 15th 77.5% | 17th 76.8% | 11th 79.3% | 5th 83.3% | 8th 81.8% | 19th 74.0% | 9th 81.5% | 12th 78.8% | 1st 86.3% | 10th 79.8% | 14th 77.8% | 15th 77.5% | 6th 82.8% | 13th 78.0% | 21st 69.7% | |
| 61.1% | 65% | 59% | 58% | 61% | 60% | 52% | 51% | 64% | 58% | 59% | 64% | 67% | 67% | 67% | 72% | 57% | 53% | 55% | 58% | 72% | 64% | |
| 86.1% | 93% | 86% | 93% | 80% | 80% | 78% | 90% | 91% | 89% | 97% | 86% | 72% | 97% | 84% | 97% | 84% | 87% | 78% | 92% | 83% | 72% | |
| 84.6% | 89% | 90% | 86% | 99% | 84% | 85% | 85% | 80% | 86% | 86% | 84% | 73% | 83% | 79% | 84% | 85% | 84% | 83% | 88% | 79% | ||
| 87.0% | 93% | 96% | 97% | 97% | 64% | 89% | 84% | 72% | 84% | 91% | 93% | 84% | 79% | 85% | 92% | 93% | 87% | 94% | 93% | 73% |