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 70.0% | 2nd 72.3% | 7th 68.3% | 11th 67.5% | 8th 68.0% | 19th 62.7% | 16th 63.7% | 10th 67.8% | 5th 69.8% | 21st 55.8% | 9th 68.0% | 12th 65.3% | 15th 64.0% | 1st 73.0% | 20th 61.2% | 14th 64.3% | 3rd 71.8% | 18th 63.2% | 6th 68.5% | 17th 63.3% | 13th 64.8% | |
| 66.3% | 65% | 69% | 66% | 66% | 69% | 62% | 74% | 74% | 70% | 62% | 67% | 75% | 62% | 67% | 49% | 60% | 74% | 68% | 66% | 61% | 67% | |
| 65.4% | 58% | 69% | 68% | 62% | 68% | 63% | 62% | 58% | 73% | 54% | 71% | 57% | 72% | 71% | 62% | 65% | 70% | 65% | 71% | 68% | 67% | |
| 47.7% | 64% | 58% | 48% | 56% | 48% | 40% | 48% | 48% | 45% | 36% | 40% | 38% | 38% | 60% | 48% | 56% | 53% | 38% | 46% | 46% | 48% | |
| 85.9% | 93% | 93% | 91% | 86% | 87% | 86% | 71% | 91% | 91% | 71% | 94% | 91% | 84% | 94% | 86% | 76% | 90% | 82% | 91% | 78% | 77% |