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 | 10th 73.5% | 13th 72.0% | 5th 77.5% | 16th 70.0% | 17th 69.5% | 18th 68.5% | 5th 77.5% | 8th 76.0% | 8th 76.0% | 20th 66.3% | 4th 77.8% | 5th 77.5% | 2nd 79.3% | 19th 68.0% | 12th 72.5% | 3rd 79.0% | 11th 73.3% | 13th 72.0% | 21st 54.5% | 1st 82.3% | 15th 70.8% | |
| 72.4% | 70% | 79% | 75% | 66% | 63% | 67% | 76% | 74% | 79% | 61% | 87% | 70% | 80% | 69% | 79% | 80% | 70% | 66% | 67% | 79% | 63% | |
| 73.0% | 63% | 73% | 75% | 63% | 78% | 70% | 77% | 82% | 68% | 67% | 75% | 80% | 80% | 63% | 80% | 77% | 74% | 74% | 63% | 80% | 71% | |
| 59.0% | 64% | 61% | 66% | 64% | 65% | 50% | 65% | 56% | 60% | 59% | 71% | 60% | 63% | 53% | 53% | 63% | 63% | 62% | 10% | 76% | 55% | |
| 87.7% | 97% | 75% | 94% | 87% | 72% | 87% | 92% | 92% | 97% | 78% | 78% | 100% | 94% | 87% | 78% | 96% | 86% | 86% | 78% | 94% | 94% |