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 | 17th 76.3% | 9th 80.0% | 20th 74.0% | 15th 76.8% | 16th 76.8% | 21st 70.8% | 6th 82.0% | 12th 77.8% | 19th 74.3% | 11th 79.3% | 2nd 84.3% | 18th 76.0% | 10th 79.5% | 8th 80.3% | 14th 77.0% | 5th 82.7% | 7th 81.3% | 13th 77.3% | 1st 84.8% | 4th 83.5% | 3rd 83.8% | |
| 73.5% | 75% | 74% | 63% | 58% | 68% | 59% | 68% | 75% | 64% | 65% | 87% | 70% | 77% | 88% | 61% | 74% | 80% | 84% | 76% | 89% | 89% | |
| 81.4% | 70% | 86% | 72% | 79% | 68% | 84% | 91% | 71% | 74% | 79% | 88% | 86% | 86% | 72% | 85% | 87% | 86% | 86% | 86% | 85% | 89% | |
| 73.6% | 74% | 82% | 83% | 77% | 77% | 63% | 76% | 72% | 66% | 81% | 77% | 57% | 69% | 68% | 75% | 84% | 68% | 67% | 87% | 71% | 72% | |
| 87.2% | 86% | 78% | 78% | 93% | 94% | 77% | 93% | 93% | 93% | 92% | 85% | 91% | 86% | 93% | 87% | 86% | 91% | 72% | 90% | 89% | 85% |