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 Kingdom. 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 | 12th 78.3% | 8th 80.0% | 19th 72.2% | 13th 77.5% | 17th 74.5% | 21st 70.3% | 5th 81.3% | 15th 76.5% | 18th 74.0% | 11th 79.0% | 2nd 83.0% | 20th 71.5% | 1st 84.5% | 13th 77.5% | 9th 79.3% | 7th 80.3% | 10th 79.0% | 16th 75.8% | 6th 81.0% | 4th 81.8% | 2nd 83.0% | |
| 72.6% | 72% | 74% | 62% | 58% | 68% | 56% | 67% | 75% | 64% | 69% | 81% | 55% | 86% | 83% | 68% | 71% | 84% | 79% | 76% | 88% | 89% | |
| 80.4% | 72% | 86% | 68% | 79% | 62% | 84% | 91% | 73% | 73% | 78% | 87% | 86% | 89% | 72% | 81% | 82% | 79% | 85% | 83% | 89% | 89% | |
| 72.0% | 78% | 82% | 83% | 80% | 77% | 64% | 74% | 65% | 66% | 79% | 77% | 60% | 77% | 64% | 82% | 79% | 68% | 52% | 78% | 61% | 67% | |
| 87.3% | 91% | 78% | 76% | 93% | 91% | 77% | 93% | 93% | 93% | 90% | 87% | 85% | 86% | 91% | 86% | 89% | 85% | 87% | 87% | 89% | 87% |