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 | 18th 69.3% | 2nd 75.3% | 11th 72.8% | 8th 73.8% | 3rd 75.3% | 13th 71.8% | 18th 69.3% | 21st 67.5% | 11th 72.8% | 13th 71.8% | 6th 74.8% | 4th 75.0% | 16th 71.3% | 1st 75.5% | 8th 73.8% | 4th 75.0% | 7th 74.5% | 17th 70.8% | 10th 73.5% | 20th 67.7% | 15th 71.7% | |
| 68.0% | 64% | 70% | 60% | 60% | 70% | 66% | 68% | 70% | 72% | 64% | 71% | 69% | 75% | 78% | 61% | 63% | 74% | 76% | 67% | 66% | 65% | |
| 73.0% | 64% | 82% | 76% | 72% | 75% | 74% | 68% | 58% | 66% | 70% | 80% | 81% | 75% | 72% | 73% | 77% | 78% | 74% | 76% | 70% | 71% | |
| 68.9% | 72% | 72% | 72% | 79% | 74% | 72% | 59% | 61% | 70% | 70% | 69% | 70% | 56% | 65% | 77% | 75% | 68% | 56% | 72% | 69% | ||
| 80.2% | 77% | 77% | 83% | 84% | 82% | 75% | 82% | 81% | 83% | 83% | 79% | 80% | 79% | 87% | 84% | 85% | 78% | 77% | 79% | 67% | 82% |