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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 19th 71.3% | 4th 79.8% | 7th 77.5% | 20th 69.0% | 12th 74.8% | 17th 71.8% | 9th 77.3% | 14th 72.5% | 16th 72.0% | 17th 71.8% | 1st 82.8% | 14th 72.5% | 2nd 80.5% | 21st 68.0% | 13th 72.5% | 2nd 80.5% | 5th 78.5% | 8th 77.5% | 6th 77.8% | 11th 76.0% | 10th 76.5% | |
| 73.1% | 70% | 80% | 67% | 57% | 65% | 56% | 75% | 65% | 73% | 67% | 86% | 60% | 83% | 69% | 72% | 87% | 90% | 77% | 83% | 70% | 83% | |
| 84.1% | 73% | 91% | 90% | 77% | 79% | 91% | 86% | 81% | 77% | 75% | 90% | 85% | 91% | 73% | 82% | 90% | 89% | 88% | 84% | 87% | 87% | |
| 62.5% | 65% | 65% | 70% | 65% | 68% | 63% | 66% | 56% | 57% | 62% | 74% | 62% | 65% | 47% | 53% | 62% | 53% | 69% | 61% | 64% | 65% | |
| 81.4% | 77% | 83% | 83% | 77% | 87% | 77% | 82% | 88% | 81% | 83% | 81% | 83% | 83% | 83% | 83% | 83% | 82% | 76% | 83% | 83% | 71% |