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 | 10th 75.8% | 8th 76.0% | 19th 71.3% | 21st 69.8% | 13th 74.3% | 17th 71.8% | 15th 72.5% | 17th 71.8% | 15th 72.5% | 20th 70.0% | 4th 80.5% | 14th 73.3% | 11th 75.3% | 5th 78.8% | 8th 76.0% | 2nd 80.8% | 1st 82.3% | 7th 76.8% | 6th 78.3% | 12th 74.8% | 2nd 80.8% | |
| 73.1% | 73% | 67% | 60% | 54% | 63% | 57% | 65% | 73% | 70% | 60% | 83% | 90% | 78% | 82% | 69% | 77% | 82% | 77% | 79% | 77% | 99% | |
| 84.9% | 77% | 90% | 83% | 83% | 77% | 90% | 81% | 76% | 75% | 75% | 91% | 73% | 87% | 88% | 89% | 96% | 96% | 89% | 87% | 90% | 90% | |
| 62.5% | 65% | 70% | 65% | 65% | 65% | 63% | 56% | 57% | 62% | 62% | 65% | 47% | 53% | 62% | 69% | 62% | 68% | 68% | 64% | 61% | 63% | |
| 81.0% | 88% | 77% | 77% | 77% | 92% | 77% | 88% | 81% | 83% | 83% | 83% | 83% | 83% | 83% | 77% | 88% | 83% | 73% | 83% | 71% | 71% |