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 | 18th 75.0% | 5th 79.0% | 11th 77.7% | 3rd 80.0% | 1st 83.7% | 20th 74.7% | 12th 77.3% | 18th 75.0% | 4th 79.7% | 9th 78.3% | 15th 76.3% | 2nd 81.0% | 16th 76.0% | 5th 79.0% | 8th 78.7% | 17th 75.3% | 14th 77.0% | 5th 79.0% | 13th 77.3% | 21st 73.3% | 10th 78.0% | |
| 82.9% | 72% | 77% | 86% | 84% | 87% | 72% | 85% | 89% | 86% | 91% | 81% | 84% | 84% | 87% | 91% | 78% | 80% | 79% | 82% | 83% | 83% | |
| 69.4% | 71% | 73% | 73% | 82% | 79% | 72% | 71% | 57% | 65% | 71% | 62% | 71% | 56% | 61% | 80% | 73% | 66% | 71% | 71% | 61% | 71% | |
| 80.8% | 82% | 87% | 74% | 74% | 85% | 80% | 76% | 79% | 88% | 73% | 86% | 88% | 88% | 89% | 65% | 75% | 85% | 87% | 79% | 76% | 80% |