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 | 1st 79.5% | 4th 77.0% | 6th 76.5% | 2nd 77.3% | 2nd 77.3% | 20th 65.3% | 16th 69.3% | 12th 71.5% | 14th 70.0% | 8th 74.0% | 11th 72.2% | 15th 69.7% | 9th 73.0% | 16th 69.3% | 4th 77.0% | 7th 75.5% | 13th 71.0% | 19th 65.3% | 9th 73.0% | 21st 63.2% | 18th 67.5% | |
| 69.5% | 73% | 73% | 69% | 69% | 69% | 57% | 69% | 72% | 66% | 72% | 69% | 77% | 72% | 75% | 74% | 73% | 69% | 63% | 69% | 60% | 69% | |
| 82.6% | 92% | 85% | 86% | 85% | 87% | 82% | 82% | 77% | 88% | 86% | 87% | 84% | 84% | 81% | 87% | 85% | 80% | 70% | 88% | 68% | 71% | |
| 65.6% | 68% | 70% | 71% | 72% | 71% | 55% | 66% | 72% | 62% | 68% | 59% | 53% | 66% | 54% | 68% | 70% | 70% | 58% | 68% | 60% | 76% | |
| 70.8% | 85% | 80% | 80% | 83% | 82% | 67% | 60% | 65% | 64% | 70% | 74% | 65% | 70% | 67% | 79% | 74% | 65% | 70% | 67% | 65% | 54% |