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 France. 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 | 4th 76.3% | 16th 68.7% | 4th 76.3% | 6th 74.0% | 1st 78.7% | 17th 67.7% | 9th 72.0% | 3rd 77.3% | 11th 70.7% | 11th 70.7% | 14th 70.3% | 7th 72.7% | 10th 71.7% | 7th 72.7% | 11th 70.7% | 19th 65.7% | 20th 64.0% | 21st 58.0% | 2nd 77.7% | 15th 69.0% | 18th 66.0% | |
| 69.0% | 73% | 59% | 73% | 73% | 86% | 57% | 73% | 79% | 73% | 76% | 59% | 69% | 73% | 73% | 74% | 61% | 65% | 63% | 73% | 59% | 59% | |
| 58.9% | 71% | 61% | 71% | 64% | 65% | 62% | 58% | 56% | 58% | 53% | 64% | 56% | 53% | 56% | 56% | 60% | 53% | 44% | 71% | 46% | ||
| 84.5% | 85% | 86% | 85% | 85% | 85% | 84% | 85% | 97% | 81% | 83% | 88% | 93% | 89% | 89% | 82% | 76% | 74% | 67% | 89% | 79% | 93% |