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 79.0% | 3rd 77.0% | 6th 76.3% | 5th 76.5% | 3rd 77.0% | 20th 65.0% | 10th 71.3% | 18th 66.5% | 16th 68.3% | 8th 73.5% | 9th 72.8% | 13th 68.8% | 12th 69.0% | 13th 68.8% | 2nd 78.8% | 7th 76.0% | 19th 66.0% | 17th 67.3% | 11th 71.2% | 21st 63.0% | 15th 68.5% | |
| 68.9% | 73% | 73% | 69% | 69% | 68% | 57% | 74% | 72% | 66% | 72% | 69% | 72% | 69% | 73% | 72% | 73% | 57% | 67% | 65% | 62% | 74% | |
| 82.7% | 90% | 85% | 85% | 85% | 87% | 82% | 82% | 76% | 80% | 86% | 87% | 84% | 85% | 82% | 89% | 85% | 77% | 79% | 84% | 72% | 74% | |
| 63.1% | 68% | 70% | 71% | 72% | 74% | 55% | 66% | 54% | 63% | 66% | 61% | 53% | 57% | 53% | 76% | 72% | 58% | 45% | 69% | 58% | 65% | |
| 71.1% | 85% | 80% | 80% | 80% | 79% | 66% | 63% | 64% | 64% | 70% | 74% | 66% | 65% | 67% | 78% | 74% | 72% | 78% | 67% | 60% | 61% |