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 | 2nd 88.0% | 6th 85.5% | 1st 88.3% | 3rd 87.0% | 14th 80.3% | 15th 79.3% | 16th 79.0% | 17th 78.5% | 12th 81.3% | 6th 85.5% | 11th 81.8% | 20th 76.5% | 13th 80.8% | 20th 76.5% | 5th 86.5% | 10th 82.8% | 19th 76.8% | 18th 78.3% | 4th 86.8% | 8th 84.0% | 9th 83.0% | |
| 73.4% | 78% | 77% | 74% | 74% | 69% | 59% | 68% | 75% | 73% | 78% | 75% | 83% | 78% | 80% | 75% | 72% | 70% | 67% | 79% | 68% | 70% | |
| 89.8% | 97% | 84% | 93% | 93% | 92% | 87% | 94% | 90% | 89% | 96% | 96% | 88% | 86% | 83% | 93% | 92% | 82% | 82% | 92% | 80% | 96% | |
| 83.4% | 86% | 91% | 94% | 90% | 92% | 87% | 72% | 78% | 82% | 87% | 78% | 65% | 77% | 76% | 87% | 88% | 72% | 82% | 92% | 95% | 80% | |
| 82.2% | 91% | 90% | 92% | 91% | 68% | 84% | 82% | 71% | 81% | 81% | 78% | 70% | 82% | 67% | 91% | 79% | 83% | 82% | 84% | 93% | 86% |