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% | 11th 74.0% | 8th 75.8% | 15th 72.5% | 17th 71.0% | 20th 66.8% | 2nd 77.0% | 9th 75.5% | 13th 72.8% | 18th 70.5% | 6th 76.8% | 4th 76.8% | 2nd 77.0% | 21st 66.3% | 10th 74.3% | 1st 78.5% | 19th 67.0% | 13th 72.8% | 7th 76.5% | 4th 76.8% | 16th 71.7% | |
| 72.9% | 78% | 79% | 75% | 66% | 75% | 60% | 77% | 73% | 71% | 75% | 79% | 70% | 80% | 69% | 75% | 80% | 72% | 66% | 79% | 65% | 66% | |
| 73.9% | 63% | 78% | 77% | 73% | 73% | 70% | 77% | 73% | 72% | 73% | 82% | 80% | 71% | 63% | 80% | 77% | 64% | 75% | 78% | 80% | 73% | |
| 60.2% | 56% | 61% | 66% | 64% | 64% | 50% | 65% | 64% | 51% | 56% | 71% | 60% | 63% | 46% | 64% | 63% | 56% | 60% | 56% | 68% | ||
| 86.5% | 97% | 78% | 85% | 87% | 72% | 87% | 89% | 92% | 97% | 78% | 75% | 97% | 94% | 87% | 78% | 94% | 76% | 90% | 93% | 94% | 76% |