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 73.5% | 6th 75.8% | 14th 72.5% | 15th 71.8% | 16th 71.0% | 20th 66.8% | 7th 75.5% | 12th 72.8% | 17th 70.5% | 4th 76.8% | 3rd 77.0% | 21st 66.3% | 10th 74.3% | 1st 78.5% | 9th 74.8% | 2nd 77.3% | 19th 67.0% | 12th 72.8% | 4th 76.8% | 18th 67.5% | 8th 75.3% | |
| 71.9% | 78% | 75% | 66% | 66% | 75% | 60% | 73% | 71% | 75% | 70% | 80% | 69% | 75% | 80% | 78% | 79% | 72% | 66% | 65% | 66% | 71% | |
| 73.9% | 63% | 77% | 73% | 78% | 73% | 70% | 73% | 72% | 73% | 80% | 71% | 63% | 80% | 77% | 78% | 76% | 64% | 75% | 80% | 73% | 82% | |
| 59.9% | 56% | 66% | 64% | 56% | 64% | 50% | 64% | 51% | 56% | 60% | 63% | 46% | 64% | 63% | 65% | 60% | 56% | 60% | 68% | 55% | 70% | |
| 86.6% | 97% | 85% | 87% | 87% | 72% | 87% | 92% | 97% | 78% | 97% | 94% | 87% | 78% | 94% | 78% | 94% | 76% | 90% | 94% | 76% | 78% |