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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 4th 71.8% | 1st 73.5% | 10th 68.3% | 7th 68.8% | 9th 68.5% | 16th 64.3% | 18th 63.7% | 11th 67.5% | 12th 67.5% | 20th 55.8% | 7th 68.8% | 14th 65.5% | 17th 64.0% | 3rd 72.0% | 21st 47.5% | 6th 69.3% | 5th 69.5% | 2nd 73.3% | 13th 67.3% | 15th 65.0% | 19th 62.3% | |
| 66.4% | 68% | 69% | 66% | 66% | 69% | 62% | 74% | 73% | 65% | 62% | 67% | 78% | 69% | 67% | 53% | 65% | 70% | 63% | 59% | 59% | 71% | |
| 65.1% | 67% | 74% | 68% | 62% | 63% | 63% | 62% | 58% | 69% | 54% | 71% | 57% | 62% | 71% | 58% | 71% | 66% | 70% | 71% | 63% | 68% | |
| 47.8% | 59% | 58% | 48% | 56% | 63% | 46% | 48% | 48% | 45% | 36% | 46% | 36% | 41% | 53% | 0% | 51% | 51% | 66% | 48% | 56% | 48% | |
| 86.1% | 93% | 93% | 91% | 91% | 79% | 86% | 71% | 91% | 91% | 71% | 91% | 91% | 84% | 97% | 79% | 90% | 91% | 94% | 91% | 82% | 62% |