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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 12th 70.0% | 7th 72.0% | 10th 70.7% | 15th 69.7% | 3rd 73.7% | 19th 65.7% | 10th 70.7% | 1st 75.3% | 2nd 75.0% | 5th 73.0% | 16th 69.3% | 6th 72.7% | 12th 70.0% | 4th 73.3% | 18th 68.0% | 12th 70.0% | 20th 65.3% | 21st 65.0% | 9th 71.7% | 17th 68.3% | 7th 72.0% | |
| 66.1% | 59% | 58% | 70% | 70% | 71% | 55% | 76% | 70% | 70% | 75% | 64% | 64% | 66% | 68% | 68% | 68% | 60% | 56% | 64% | 61% | 76% | |
| 70.2% | 74% | 81% | 75% | 72% | 72% | 75% | 56% | 72% | 73% | 72% | 61% | 72% | 64% | 69% | 75% | 71% | 61% | 64% | 75% | 63% | 77% | |
| 75.3% | 77% | 77% | 67% | 67% | 78% | 67% | 80% | 84% | 82% | 72% | 83% | 82% | 80% | 83% | 61% | 71% | 75% | 75% | 76% | 81% | 63% |