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 | 16th 70.8% | 6th 75.8% | 8th 73.0% | 20th 69.8% | 15th 71.0% | 8th 73.0% | 16th 70.8% | 19th 70.5% | 14th 71.5% | 16th 70.8% | 2nd 80.5% | 21st 68.0% | 8th 73.0% | 3rd 77.5% | 12th 72.8% | 8th 73.0% | 5th 77.0% | 7th 73.5% | 3rd 77.5% | 13th 72.0% | 1st 81.3% | |
| 70.9% | 73% | 66% | 67% | 54% | 63% | 56% | 62% | 70% | 69% | 60% | 83% | 69% | 75% | 77% | 63% | 64% | 87% | 82% | 72% | 77% | 99% | |
| 83.0% | 68% | 90% | 83% | 83% | 78% | 96% | 81% | 77% | 75% | 78% | 91% | 73% | 78% | 90% | 83% | 83% | 87% | 86% | 90% | 84% | 90% | |
| 61.0% | 65% | 70% | 65% | 65% | 65% | 63% | 57% | 57% | 59% | 62% | 65% | 47% | 56% | 62% | 62% | 62% | 61% | 53% | 65% | 56% | 65% | |
| 78.9% | 77% | 77% | 77% | 77% | 78% | 77% | 83% | 78% | 83% | 83% | 83% | 83% | 83% | 81% | 83% | 83% | 73% | 73% | 83% | 71% | 71% |