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 | 11th 72.3% | 4th 77.3% | 8th 73.8% | 13th 71.8% | 16th 69.8% | 21st 67.5% | 3rd 78.0% | 6th 75.0% | 20th 68.0% | 7th 74.0% | 4th 77.3% | 18th 68.8% | 15th 70.0% | 2nd 79.5% | 14th 71.0% | 12th 72.0% | 19th 68.5% | 10th 72.7% | 1st 80.0% | 17th 69.2% | 9th 73.5% | |
| 69.8% | 70% | 75% | 66% | 66% | 69% | 60% | 74% | 79% | 65% | 68% | 72% | 79% | 79% | 81% | 60% | 71% | 67% | 60% | 70% | 67% | 67% | |
| 73.6% | 63% | 74% | 78% | 78% | 73% | 70% | 82% | 68% | 73% | 75% | 80% | 63% | 70% | 80% | 78% | 80% | 73% | 75% | 80% | 58% | 75% | |
| 60.6% | 64% | 66% | 64% | 56% | 65% | 50% | 64% | 56% | 56% | 56% | 63% | 46% | 53% | 63% | 60% | 52% | 40% | 70% | 76% | 76% | 76% | |
| 87.4% | 92% | 94% | 87% | 87% | 72% | 90% | 92% | 97% | 78% | 97% | 94% | 87% | 78% | 94% | 86% | 85% | 94% | 86% | 94% | 76% | 76% |