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 | 4th 85.3% | 12th 82.0% | 1st 88.5% | 2nd 88.3% | 19th 79.5% | 17th 80.0% | 8th 83.7% | 18th 79.5% | 20th 77.3% | 11th 82.5% | 7th 84.0% | 2nd 88.3% | 9th 83.2% | 13th 81.8% | 15th 81.0% | 21st 77.0% | 16th 80.3% | 14th 81.3% | 10th 83.0% | 5th 84.5% | 5th 84.5% | |
| 74.0% | 76% | 72% | 77% | 74% | 69% | 59% | 70% | 68% | 76% | 77% | 80% | 81% | 77% | 80% | 74% | 80% | 72% | 67% | 73% | 76% | 76% | |
| 91.0% | 95% | 90% | 96% | 93% | 92% | 87% | 91% | 96% | 90% | 89% | 92% | 99% | 96% | 88% | 92% | 83% | 84% | 84% | 93% | 88% | 93% | |
| 82.2% | 83% | 75% | 90% | 94% | 79% | 90% | 90% | 72% | 76% | 83% | 74% | 87% | 78% | 73% | 73% | 73% | 84% | 89% | 86% | 90% | 87% | |
| 83.3% | 87% | 91% | 91% | 92% | 78% | 84% | 84% | 82% | 67% | 81% | 90% | 86% | 82% | 86% | 85% | 72% | 81% | 85% | 80% | 84% | 82% |