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 | 7th 75.3% | 4th 77.5% | 13th 73.8% | 13th 73.8% | 17th 71.0% | 20th 68.3% | 3rd 77.8% | 8th 75.0% | 19th 68.8% | 10th 74.8% | 8th 75.0% | 21st 65.0% | 16th 71.5% | 1st 79.3% | 5th 76.0% | 11th 74.5% | 12th 74.0% | 15th 72.7% | 2nd 78.8% | 6th 75.3% | 18th 69.8% | |
| 71.0% | 78% | 75% | 66% | 66% | 63% | 60% | 74% | 73% | 75% | 62% | 72% | 69% | 75% | 80% | 75% | 72% | 76% | 70% | 65% | 72% | 73% | |
| 75.1% | 67% | 75% | 78% | 78% | 78% | 70% | 82% | 72% | 66% | 80% | 71% | 63% | 80% | 80% | 77% | 80% | 73% | 75% | 80% | 78% | 75% | |
| 60.2% | 64% | 66% | 64% | 64% | 65% | 53% | 63% | 60% | 56% | 60% | 63% | 41% | 53% | 63% | 58% | 60% | 56% | 64% | 76% | 55% | ||
| 87.7% | 92% | 94% | 87% | 87% | 78% | 90% | 92% | 95% | 78% | 97% | 94% | 87% | 78% | 94% | 94% | 86% | 91% | 82% | 94% | 76% | 76% |