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 | 1st 78.8% | 3rd 77.0% | 5th 75.5% | 4th 77.0% | 2nd 78.8% | 20th 65.3% | 14th 69.3% | 17th 68.8% | 12th 70.5% | 7th 75.0% | 10th 73.5% | 18th 68.5% | 9th 74.3% | 16th 69.2% | 6th 75.5% | 8th 74.5% | 19th 66.3% | 14th 69.3% | 11th 72.8% | 21st 57.0% | 13th 70.3% | |
| 69.3% | 72% | 73% | 69% | 69% | 69% | 57% | 69% | 72% | 69% | 72% | 70% | 72% | 75% | 75% | 68% | 67% | 67% | 69% | 65% | 62% | 75% | |
| 83.0% | 90% | 85% | 85% | 85% | 87% | 82% | 82% | 76% | 79% | 87% | 86% | 84% | 89% | 82% | 88% | 81% | 75% | 70% | 86% | 82% | ||
| 65.3% | 68% | 70% | 68% | 72% | 77% | 55% | 66% | 63% | 70% | 69% | 60% | 53% | 66% | 53% | 70% | 76% | 58% | 73% | 68% | 56% | 60% | |
| 70.6% | 85% | 80% | 80% | 82% | 82% | 67% | 60% | 64% | 64% | 72% | 78% | 65% | 67% | 67% | 76% | 74% | 65% | 65% | 72% | 53% | 64% |