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 | 3rd 87.3% | 1st 88.5% | 2nd 88.3% | 4th 86.3% | 10th 83.8% | 17th 80.3% | 18th 79.0% | 21st 76.8% | 14th 82.0% | 4th 86.3% | 13th 82.5% | 19th 78.5% | 9th 84.8% | 20th 78.0% | 8th 85.3% | 11th 83.0% | 12th 82.8% | 16th 81.5% | 6th 86.0% | 6th 86.0% | 15th 81.8% | |
| 74.4% | 77% | 77% | 74% | 74% | 69% | 59% | 68% | 77% | 77% | 75% | 78% | 83% | 82% | 80% | 72% | 73% | 76% | 67% | 79% | 76% | 70% | |
| 92.2% | 96% | 96% | 93% | 93% | 94% | 90% | 96% | 90% | 89% | 99% | 93% | 88% | 93% | 92% | 94% | 94% | 89% | 87% | 88% | 87% | 95% | |
| 83.2% | 86% | 90% | 94% | 86% | 93% | 88% | 73% | 73% | 81% | 87% | 78% | 73% | 75% | 73% | 88% | 85% | 79% | 82% | 93% | 88% | 83% | |
| 83.1% | 90% | 91% | 92% | 92% | 79% | 84% | 79% | 67% | 81% | 84% | 81% | 70% | 89% | 67% | 87% | 80% | 87% | 90% | 84% | 93% | 79% |