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 Japan. 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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 4th 71.5% | 3rd 72.3% | 7th 68.3% | 10th 67.5% | 6th 68.8% | 15th 64.3% | 18th 63.2% | 12th 65.5% | 1st 72.8% | 21st 54.5% | 8th 68.0% | 11th 66.3% | 17th 63.5% | 1st 72.8% | 19th 61.2% | 16th 64.0% | 13th 65.3% | 9th 67.8% | 5th 69.0% | 14th 64.5% | 20th 61.0% | |
| 65.2% | 67% | 69% | 66% | 66% | 64% | 62% | 74% | 65% | 71% | 55% | 67% | 78% | 68% | 70% | 52% | 59% | 69% | 58% | 66% | 60% | 64% | |
| 65.0% | 64% | 69% | 68% | 62% | 73% | 63% | 62% | 58% | 73% | 54% | 71% | 50% | 64% | 71% | 65% | 65% | 62% | 71% | 71% | 66% | 63% | |
| 48.6% | 64% | 58% | 48% | 56% | 48% | 46% | 46% | 48% | 56% | 38% | 40% | 46% | 38% | 53% | 42% | 53% | 41% | 51% | 48% | 53% | 47% | |
| 86.3% | 91% | 93% | 91% | 86% | 90% | 86% | 71% | 91% | 91% | 71% | 94% | 91% | 84% | 97% | 86% | 79% | 89% | 91% | 91% | 79% | 70% |