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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 75.3% | 5th 75.0% | 14th 71.0% | 7th 74.3% | 9th 73.3% | 20th 61.0% | 17th 67.0% | 10th 72.3% | 12th 71.3% | 21st 59.0% | 12th 71.3% | 3rd 75.3% | 15th 69.0% | 2nd 75.3% | 19th 63.0% | 11th 71.7% | 7th 74.3% | 18th 66.3% | 1st 76.0% | 6th 74.7% | 16th 68.7% | |
| 89.5% | 82% | 97% | 94% | 94% | 93% | 79% | 80% | 93% | 94% | 80% | 84% | 90% | 94% | 93% | 87% | 94% | 93% | 84% | 94% | 94% | 87% | |
| 69.2% | 81% | 73% | 68% | 80% | 72% | 61% | 65% | 65% | 66% | 54% | 65% | 79% | 53% | 71% | 72% | 71% | 68% | 63% | 79% | 72% | 75% | |
| 53.5% | 63% | 55% | 51% | 49% | 55% | 43% | 56% | 59% | 54% | 43% | 65% | 57% | 60% | 62% | 30% | 50% | 62% | 52% | 55% | 58% | 44% |