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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 15th 78.0% | 6th 81.8% | 11th 80.3% | 19th 73.8% | 20th 73.0% | 21st 71.8% | 13th 78.5% | 10th 80.3% | 17th 76.3% | 18th 76.0% | 4th 82.7% | 16th 77.3% | 3rd 82.8% | 14th 78.3% | 2nd 83.5% | 9th 80.5% | 12th 78.8% | 8th 80.7% | 5th 82.5% | 7th 81.5% | 1st 84.3% | |
| 76.5% | 75% | 87% | 74% | 62% | 68% | 59% | 78% | 67% | 75% | 72% | 94% | 65% | 81% | 70% | 87% | 88% | 79% | 79% | 87% | 76% | 84% | |
| 79.1% | 70% | 73% | 86% | 72% | 62% | 87% | 78% | 87% | 71% | 73% | 83% | 76% | 86% | 86% | 86% | 72% | 79% | 86% | 82% | 85% | 82% | |
| 74.1% | 82% | 82% | 82% | 83% | 77% | 64% | 74% | 74% | 64% | 66% | 82% | 78% | 77% | 66% | 70% | 69% | 74% | 70% | 70% | 78% | ||
| 86.4% | 85% | 85% | 79% | 78% | 85% | 77% | 84% | 93% | 95% | 93% | 72% | 90% | 87% | 91% | 91% | 93% | 83% | 88% | 91% | 87% | 87% |