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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 86.8% | 7th 84.7% | 2nd 88.0% | 5th 85.8% | 14th 81.0% | 18th 79.0% | 15th 79.5% | 15th 79.5% | 11th 82.0% | 3rd 86.8% | 12th 81.8% | 19th 77.8% | 10th 82.3% | 21st 75.8% | 8th 83.0% | 9th 83.0% | 20th 75.8% | 17th 79.0% | 6th 85.0% | 13th 81.5% | 1st 89.0% | |
| 74.0% | 77% | 77% | 74% | 74% | 69% | 57% | 68% | 77% | 77% | 79% | 75% | 80% | 75% | 80% | 73% | 74% | 72% | 72% | 76% | 69% | 80% | |
| 89.2% | 92% | 84% | 92% | 93% | 94% | 87% | 94% | 90% | 89% | 96% | 93% | 88% | 87% | 83% | 89% | 91% | 84% | 84% | 87% | 81% | 95% | |
| 83.1% | 86% | 90% | 94% | 87% | 93% | 88% | 71% | 78% | 81% | 88% | 78% | 73% | 78% | 73% | 87% | 83% | 72% | 73% | 93% | 86% | 94% | |
| 82.5% | 92% | 88% | 92% | 89% | 68% | 84% | 85% | 73% | 81% | 84% | 81% | 70% | 89% | 67% | 83% | 84% | 75% | 87% | 84% | 90% | 87% |