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 3.7 Sonnet | Claude 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 12th 73.5% | 10th 74.5% | 4th 78.3% | 13th 72.5% | 15th 71.5% | 21st 67.5% | 1st 80.0% | 7th 76.8% | 6th 77.0% | 18th 70.3% | 8th 76.7% | 14th 72.0% | 5th 77.3% | 20th 68.0% | 15th 71.5% | 3rd 79.3% | 19th 68.3% | 11th 74.0% | 9th 75.0% | 2nd 80.0% | 17th 71.0% | |
| 72.0% | 70% | 79% | 75% | 66% | 66% | 60% | 78% | 74% | 79% | 65% | 73% | 70% | 72% | 69% | 75% | 80% | 68% | 68% | 80% | 70% | 74% | |
| 74.4% | 63% | 78% | 78% | 73% | 78% | 70% | 77% | 82% | 72% | 66% | 82% | 80% | 80% | 63% | 80% | 80% | 72% | 75% | 70% | 80% | 63% | |
| 62.4% | 64% | 63% | 66% | 64% | 64% | 50% | 74% | 63% | 60% | 56% | 76% | 60% | 63% | 46% | 53% | 63% | 56% | 66% | 56% | 76% | 71% | |
| 87.4% | 97% | 78% | 94% | 87% | 78% | 90% | 91% | 88% | 97% | 94% | 76% | 78% | 94% | 94% | 78% | 94% | 77% | 87% | 94% | 94% | 76% |