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 United States. 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 | 9th 81.5% | 8th 81.8% | 5th 82.8% | 18th 79.2% | 20th 78.3% | 21st 75.0% | 3rd 83.5% | 15th 80.3% | 14th 80.3% | 19th 78.3% | 1st 88.5% | 13th 80.5% | 2nd 84.8% | 7th 82.0% | 9th 81.5% | 4th 83.0% | 16th 79.8% | 17th 79.5% | 12th 80.8% | 6th 82.0% | 11th 81.3% | |
| 86.1% | 84% | 87% | 83% | 80% | 81% | 77% | 93% | 81% | 87% | 86% | 98% | 80% | 92% | 85% | 88% | 94% | 82% | 86% | 89% | 88% | ||
| 87.0% | 88% | 90% | 96% | 85% | 79% | 86% | 88% | 90% | 81% | 76% | 90% | 83% | 93% | 89% | 88% | 83% | 90% | 90% | 87% | 88% | 88% | |
| 66.9% | 70% | 69% | 70% | 70% | 70% | 59% | 72% | 62% | 60% | 60% | 76% | 71% | 69% | 69% | 68% | 62% | 60% | 66% | 67% | 69% | 66% | |
| 84.9% | 84% | 81% | 82% | 82% | 83% | 78% | 81% | 88% | 93% | 91% | 90% | 88% | 85% | 85% | 82% | 93% | 87% | 76% | 80% | 83% | 90% |