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 GD2 (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 | 9th 69.7% | 9th 69.7% | 8th 70.7% | 9th 69.7% | 1st 78.3% | 17th 67.7% | 9th 69.7% | 2nd 75.3% | 13th 69.3% | 5th 71.7% | 3rd 73.3% | 4th 72.0% | 16th 68.3% | 14th 69.0% | 20th 65.0% | 7th 71.0% | 18th 67.0% | 21st 60.0% | 5th 71.7% | 19th 65.0% | 14th 69.0% | |
| 66.2% | 59% | 58% | 70% | 70% | 80% | 55% | 76% | 70% | 70% | 75% | 64% | 64% | 70% | 64% | 70% | 60% | 60% | 60% | 68% | 61% | 67% | |
| 68.1% | 74% | 74% | 75% | 72% | 75% | 81% | 56% | 72% | 56% | 68% | 73% | 69% | 58% | 63% | 66% | 76% | 61% | 54% | 75% | 65% | 68% | |
| 74.6% | 76% | 77% | 67% | 67% | 80% | 67% | 77% | 84% | 82% | 72% | 83% | 83% | 77% | 80% | 59% | 77% | 80% | 66% | 72% | 69% | 72% |