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 | 16th 71.5% | 2nd 78.0% | 11th 72.5% | 14th 71.8% | 9th 74.3% | 20th 68.0% | 2nd 78.0% | 12th 72.3% | 21st 67.5% | 17th 70.8% | 5th 77.5% | 19th 68.8% | 18th 70.0% | 4th 77.8% | 14th 71.8% | 7th 76.8% | 10th 74.0% | 5th 77.5% | 1st 80.0% | 13th 72.0% | 8th 76.0% | |
| 71.4% | 78% | 75% | 66% | 66% | 69% | 60% | 74% | 68% | 75% | 70% | 80% | 69% | 79% | 81% | 61% | 76% | 71% | 70% | 70% | 71% | 71% | |
| 75.1% | 67% | 77% | 73% | 78% | 78% | 72% | 82% | 68% | 66% | 75% | 80% | 73% | 70% | 71% | 73% | 80% | 75% | 77% | 80% | 80% | 82% | |
| 60.2% | 56% | 66% | 64% | 56% | 60% | 50% | 64% | 56% | 51% | 60% | 56% | 46% | 53% | 63% | 56% | 60% | 63% | 70% | 76% | 63% | 76% | |
| 87.8% | 85% | 94% | 87% | 87% | 90% | 90% | 92% | 97% | 78% | 78% | 94% | 87% | 78% | 96% | 97% | 91% | 87% | 93% | 94% | 74% | 75% |