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 Italy. 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 | 12th 73.0% | 9th 76.0% | 12th 73.0% | 20th 69.8% | 17th 70.8% | 15th 72.0% | 14th 72.5% | 19th 70.5% | 16th 71.0% | 17th 70.8% | 1st 80.5% | 21st 68.0% | 11th 74.5% | 2nd 80.0% | 10th 75.3% | 6th 77.0% | 3rd 79.5% | 5th 77.5% | 7th 76.5% | 8th 76.3% | 4th 77.5% | |
| 72.1% | 73% | 67% | 67% | 54% | 63% | 57% | 65% | 72% | 67% | 60% | 83% | 69% | 72% | 87% | 69% | 66% | 82% | 90% | 72% | 90% | 90% | |
| 84.0% | 71% | 90% | 83% | 83% | 77% | 91% | 81% | 75% | 75% | 78% | 91% | 73% | 87% | 88% | 85% | 91% | 95% | 86% | 87% | 90% | 88% | |
| 61.0% | 65% | 70% | 65% | 65% | 65% | 63% | 56% | 57% | 59% | 62% | 65% | 47% | 56% | 62% | 64% | 68% | 52% | 58% | 64% | 56% | 61% | |
| 80.3% | 83% | 77% | 77% | 77% | 78% | 77% | 88% | 78% | 83% | 83% | 83% | 83% | 83% | 83% | 83% | 83% | 89% | 76% | 83% | 69% | 71% |