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 | Grok 4 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 12th 82.7% | 5th 84.7% | 7th 84.0% | 9th 83.0% | 12th 82.7% | 18th 79.0% | 17th 80.0% | 14th 81.0% | 10th 82.7% | 7th 84.0% | 10th 82.7% | 2nd 86.3% | 15th 80.3% | 3rd 86.0% | 3rd 86.0% | 6th 84.3% | 19th 77.3% | 21st 71.3% | 1st 87.0% | 20th 74.3% | 15th 80.3% | |
| 86.9% | 90% | 88% | 84% | 84% | 86% | 81% | 86% | 85% | 90% | 90% | 93% | 93% | 86% | 93% | 93% | 89% | 82% | 61% | 91% | 90% | 90% | |
| 79.2% | 84% | 85% | 88% | 84% | 80% | 77% | 79% | 77% | 80% | 81% | 79% | 76% | 68% | 78% | 84% | 82% | 74% | 80% | 86% | 61% | 80% | |
| 79.6% | 74% | 81% | 80% | 81% | 82% | 79% | 75% | 81% | 78% | 81% | 76% | 90% | 87% | 87% | 81% | 82% | 76% | 73% | 84% | 72% | 71% |