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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 1st 88.0% | 14th 81.8% | 5th 85.5% | 2nd 87.5% | 17th 78.3% | 15th 81.3% | 6th 85.2% | 16th 79.8% | 20th 77.8% | 11th 82.8% | 7th 85.0% | 3rd 87.0% | 10th 83.0% | 13th 82.3% | 9th 84.0% | 19th 78.0% | 17th 78.3% | 21st 73.0% | 8th 84.5% | 4th 85.8% | 12th 82.5% | |
| 75.7% | 82% | 71% | 77% | 74% | 69% | 66% | 78% | 68% | 76% | 80% | 80% | 77% | 78% | 83% | 79% | 80% | 76% | 72% | 76% | 76% | 72% | |
| 90.0% | 96% | 90% | 84% | 90% | 87% | 87% | 91% | 96% | 91% | 89% | 94% | 99% | 95% | 88% | 87% | 92% | 86% | 84% | 92% | 90% | 82% | |
| 81.0% | 85% | 75% | 90% | 94% | 79% | 88% | 90% | 72% | 77% | 81% | 76% | 87% | 78% | 73% | 81% | 73% | 72% | 58% | 86% | 93% | 94% | |
| 83.0% | 89% | 91% | 91% | 92% | 78% | 84% | 82% | 83% | 67% | 81% | 90% | 85% | 81% | 85% | 89% | 67% | 79% | 78% | 84% | 84% | 82% |