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 76.5% | 9th 79.0% | 20th 73.8% | 13th 78.3% | 16th 77.0% | 21st 70.3% | 4th 81.8% | 18th 76.3% | 19th 74.0% | 12th 78.5% | 2nd 82.0% | 15th 77.5% | 3rd 82.0% | 8th 79.3% | 10th 79.0% | 6th 80.5% | 14th 78.0% | 11th 78.8% | 7th 80.3% | 5th 80.5% | 1st 86.3% | |
| 72.4% | 72% | 70% | 65% | 65% | 68% | 56% | 67% | 75% | 64% | 65% | 81% | 70% | 81% | 88% | 63% | 71% | 84% | 79% | 73% | 75% | 89% | |
| 81.2% | 70% | 86% | 72% | 79% | 68% | 84% | 91% | 73% | 73% | 82% | 86% | 89% | 86% | 72% | 85% | 85% | 82% | 84% | 85% | 89% | 85% | |
| 72.7% | 79% | 82% | 83% | 76% | 79% | 64% | 76% | 64% | 66% | 80% | 74% | 60% | 75% | 64% | 82% | 74% | 61% | 63% | 77% | 75% | ||
| 87.1% | 85% | 78% | 75% | 93% | 93% | 77% | 93% | 93% | 93% | 87% | 87% | 91% | 86% | 93% | 86% | 92% | 85% | 89% | 86% | 83% | 85% |