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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 1st 78.3% | 9th 72.7% | 4th 76.3% | 2nd 77.0% | 8th 73.3% | 18th 68.0% | 5th 75.3% | 2nd 77.0% | 15th 71.0% | 17th 70.7% | 12th 72.0% | 9th 72.7% | 13th 71.7% | 6th 74.0% | 14th 71.3% | 11th 72.3% | 20th 62.3% | 18th 68.0% | 6th 74.0% | 21st 60.3% | 15th 71.0% | |
| 68.5% | 84% | 67% | 73% | 73% | 73% | 57% | 73% | 79% | 73% | 76% | 59% | 69% | 73% | 73% | 74% | 66% | 54% | 65% | 62% | 53% | 62% | |
| 59.6% | 64% | 61% | 71% | 73% | 60% | 59% | 61% | 55% | 59% | 53% | 69% | 56% | 53% | 56% | 63% | 58% | 51% | 51% | 71% | 50% | 58% | |
| 87.5% | 87% | 90% | 85% | 85% | 87% | 88% | 92% | 97% | 81% | 83% | 88% | 93% | 89% | 93% | 77% | 93% | 82% | 88% | 89% | 78% | 93% |