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 GD2 (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 80.7% | 3rd 79.7% | 5th 78.3% | 4th 79.0% | 1st 81.0% | 18th 68.7% | 16th 70.0% | 10th 74.0% | 14th 71.7% | 7th 76.3% | 11th 72.3% | 20th 68.0% | 18th 68.7% | 17th 69.7% | 6th 77.7% | 9th 75.0% | 13th 72.0% | 8th 75.7% | 11th 72.3% | 21st 64.0% | 14th 71.7% | |
| 79.9% | 94% | 88% | 88% | 90% | 91% | 76% | 68% | 78% | 82% | 82% | 83% | 74% | 72% | 75% | 81% | 81% | 80% | 85% | 75% | 66% | 68% | |
| 68.6% | 69% | 73% | 73% | 73% | 79% | 67% | 69% | 65% | 67% | 71% | 63% | 55% | 61% | 56% | 80% | 76% | 70% | 69% | 73% | 60% | 72% | |
| 72.4% | 79% | 78% | 74% | 74% | 73% | 63% | 73% | 79% | 66% | 76% | 71% | 75% | 73% | 78% | 72% | 68% | 66% | 73% | 69% | 66% | 75% |