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 | 1st 79.3% | 3rd 75.0% | 17th 69.0% | 13th 70.7% | 11th 71.7% | 20th 64.3% | 9th 72.7% | 3rd 75.0% | 17th 69.0% | 12th 71.0% | 3rd 75.0% | 6th 74.7% | 7th 73.0% | 2nd 78.3% | 21st 61.3% | 19th 67.3% | 15th 70.0% | 13th 70.7% | 7th 73.0% | 10th 71.7% | 16th 69.7% | |
| 84.0% | 93% | 85% | 80% | 84% | 94% | 80% | 89% | 93% | 84% | 89% | 84% | 89% | 89% | 91% | 87% | 75% | 80% | 75% | 84% | 87% | 51% | |
| 75.9% | 79% | 80% | 78% | 79% | 78% | 69% | 71% | 72% | 74% | 75% | 78% | 78% | 68% | 77% | 65% | 72% | 72% | 75% | 79% | 81% | 93% | |
| 54.8% | 66% | 60% | 49% | 49% | 43% | 44% | 58% | 60% | 49% | 49% | 63% | 57% | 62% | 67% | 32% | 55% | 58% | 62% | 56% | 47% | 65% |