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 India. 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 | 4th 87.3% | 2nd 88.8% | 1st 89.0% | 5th 85.8% | 7th 85.0% | 13th 79.8% | 17th 78.0% | 17th 78.0% | 9th 82.0% | 3rd 87.8% | 8th 82.5% | 19th 77.8% | 14th 79.5% | 16th 78.8% | 6th 85.5% | 10th 81.0% | 20th 75.0% | 15th 79.3% | 11th 80.3% | 12th 80.0% | 21st 70.0% | |
| 72.9% | 79% | 77% | 74% | 74% | 69% | 59% | 68% | 76% | 77% | 81% | 78% | 80% | 78% | 80% | 75% | 69% | 70% | 62% | 68% | 67% | 70% | |
| 90.4% | 96% | 96% | 96% | 93% | 92% | 87% | 94% | 91% | 89% | 99% | 96% | 88% | 87% | 92% | 90% | 90% | 79% | 82% | 87% | 84% | ||
| 82.4% | 85% | 91% | 94% | 87% | 93% | 89% | 72% | 77% | 81% | 87% | 75% | 73% | 68% | 76% | 91% | 84% | 72% | 86% | 88% | 80% | ||
| 82.3% | 89% | 91% | 92% | 89% | 86% | 84% | 78% | 68% | 81% | 84% | 81% | 70% | 85% | 67% | 86% | 81% | 79% | 87% | 78% | 89% |