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 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 75.5% | 6th 76.0% | 16th 70.0% | 14th 71.8% | 19th 67.2% | 18th 67.5% | 4th 77.8% | 5th 76.8% | 20th 65.3% | 9th 75.5% | 3rd 79.0% | 21st 65.3% | 17th 69.0% | 2nd 79.3% | 12th 73.0% | 7th 75.8% | 13th 72.8% | 11th 74.0% | 1st 80.0% | 15th 70.2% | 10th 75.0% | |
| 70.5% | 78% | 75% | 66% | 66% | 69% | 60% | 74% | 79% | 61% | 70% | 79% | 70% | 75% | 83% | 64% | 70% | 70% | 66% | 70% | 66% | 70% | |
| 72.8% | 63% | 78% | 63% | 78% | 63% | 70% | 82% | 71% | 66% | 75% | 80% | 63% | 70% | 80% | 77% | 76% | 71% | 75% | 80% | 69% | 79% | |
| 61.1% | 64% | 66% | 64% | 56% | 65% | 50% | 63% | 60% | 56% | 60% | 63% | 41% | 53% | 60% | 57% | 64% | 63% | 71% | 76% | 70% | ||
| 87.6% | 97% | 85% | 87% | 87% | 72% | 90% | 92% | 97% | 78% | 97% | 94% | 87% | 78% | 94% | 94% | 93% | 87% | 84% | 94% | 76% | 76% |