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 Germany. 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 | 7th 73.5% | 1st 78.8% | 6th 74.8% | 11th 72.5% | 5th 74.8% | 8th 73.3% | 21st 58.3% | 16th 69.0% | 10th 73.0% | 16th 69.0% | 2nd 75.0% | 2nd 75.0% | 15th 70.3% | 2nd 75.0% | 18th 68.8% | 9th 73.0% | 13th 72.0% | 14th 71.0% | 12th 72.3% | 20th 66.0% | 19th 66.8% | |
| 73.0% | 77% | 75% | 75% | 67% | 77% | 65% | 79% | 80% | 77% | 66% | 75% | 80% | 78% | 83% | 60% | 73% | 78% | 73% | 71% | 58% | 67% | |
| 65.2% | 59% | 76% | 63% | 63% | 75% | 72% | 69% | 50% | 61% | 63% | 68% | 72% | 68% | 66% | 63% | 66% | 67% | 60% | 68% | 60% | 61% | |
| 78.8% | 81% | 87% | 88% | 88% | 77% | 81% | 75% | 74% | 82% | 75% | 79% | 78% | 67% | 76% | 83% | 80% | 75% | 73% | 82% | 79% | 75% | |
| 69.0% | 77% | 77% | 73% | 72% | 70% | 75% | 10% | 72% | 72% | 72% | 78% | 70% | 68% | 75% | 69% | 73% | 68% | 78% | 68% | 67% | 64% |