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 GD2 (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 | 5th 76.0% | 8th 74.7% | 16th 69.7% | 10th 74.3% | 2nd 76.7% | 20th 60.7% | 18th 67.0% | 5th 76.0% | 3rd 76.3% | 21st 60.3% | 11th 73.7% | 1st 78.3% | 13th 70.7% | 7th 75.3% | 19th 66.0% | 15th 70.0% | 13th 70.7% | 16th 69.7% | 4th 76.0% | 12th 73.0% | 9th 74.7% | |
| 91.0% | 82% | 97% | 94% | 94% | 94% | 79% | 80% | 98% | 97% | 88% | 84% | 94% | 94% | 93% | 87% | 93% | 93% | 88% | 94% | 94% | 94% | |
| 69.8% | 79% | 72% | 68% | 80% | 78% | 60% | 65% | 65% | 72% | 54% | 72% | 79% | 63% | 71% | 72% | 72% | 59% | 63% | 79% | 71% | 72% | |
| 54.9% | 67% | 55% | 47% | 49% | 58% | 43% | 56% | 65% | 60% | 39% | 65% | 62% | 55% | 62% | 39% | 45% | 60% | 58% | 55% | 54% | 58% |