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 | 8th 74.0% | 3rd 74.7% | 14th 70.0% | 7th 74.3% | 5th 74.7% | 19th 61.0% | 18th 67.0% | 9th 73.0% | 16th 69.0% | 21st 57.7% | 11th 71.3% | 2nd 76.0% | 15th 69.3% | 9th 73.0% | 20th 59.7% | 13th 70.0% | 11th 71.3% | 6th 74.3% | 1st 77.7% | 3rd 74.7% | 17th 67.7% | |
| 89.7% | 91% | 97% | 94% | 94% | 93% | 79% | 80% | 97% | 84% | 80% | 84% | 95% | 94% | 93% | 87% | 94% | 93% | 88% | 94% | 92% | 80% | |
| 68.2% | 72% | 72% | 65% | 80% | 72% | 61% | 65% | 65% | 72% | 54% | 65% | 79% | 59% | 64% | 60% | 79% | 59% | 80% | 79% | 66% | 65% | |
| 53.6% | 59% | 55% | 51% | 49% | 59% | 43% | 56% | 57% | 51% | 39% | 65% | 54% | 55% | 62% | 32% | 37% | 62% | 55% | 60% | 66% | 58% |