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 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 | 1st 85.3% | 14th 76.7% | 17th 74.7% | 6th 79.0% | 4th 80.7% | 20th 70.3% | 18th 74.3% | 6th 79.0% | 15th 76.3% | 10th 78.0% | 5th 79.7% | 16th 75.3% | 8th 78.7% | 3rd 81.3% | 13th 77.0% | 11th 77.7% | 19th 73.7% | 9th 78.3% | 2nd 82.3% | 11th 77.7% | 21st 67.3% | |
| 81.5% | 94% | 82% | 73% | 89% | 91% | 72% | 83% | 89% | 86% | 87% | 81% | 84% | 87% | 84% | 88% | 88% | 70% | 84% | 81% | 75% | 44% | |
| 66.0% | 75% | 64% | 75% | 69% | 74% | 60% | 64% | 57% | 62% | 68% | 65% | 59% | 57% | 64% | 72% | 66% | 62% | 62% | 75% | 69% | 66% | |
| 84.4% | 87% | 84% | 76% | 79% | 77% | 79% | 76% | 91% | 81% | 79% | 93% | 83% | 92% | 96% | 71% | 79% | 89% | 89% | 91% | 89% | 92% |