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 Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o Mini | Qwen3 30b A3B Instruct 2507 | Qwen3 Next 80b A3B Instruct | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 78.3% | 8th 72.5% | 7th 73.0% | 11th 68.0% | 10th 68.3% | 4th 76.0% | 12th 67.5% | 9th 69.5% | 1st 79.3% | 13th 65.3% | 1st 79.3% | 5th 74.0% | 6th 73.0% | |
| 68.8% | 75% | 66% | 66% | 66% | 60% | 66% | 61% | 70% | 80% | 70% | 80% | 70% | 65% | |
| 74.8% | 78% | 73% | 78% | 63% | 70% | 82% | 75% | 70% | 80% | 63% | 80% | 80% | 80% | |
| 60.7% | 66% | 64% | 56% | 65% | 53% | 64% | 56% | 60% | 63% | 41% | 63% | 68% | 70% | |
| 86.1% | 94% | 87% | 92% | 78% | 90% | 92% | 78% | 78% | 94% | 87% | 94% | 78% | 77% |