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 Rural. 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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 11th 84.0% | 1st 87.5% | 20th 80.3% | 10th 84.5% | 7th 85.8% | 18th 80.5% | 13th 83.3% | 21st 79.0% | 17th 82.3% | 8th 85.5% | 1st 87.5% | 19th 80.5% | 3rd 87.3% | 6th 85.8% | 15th 82.8% | 4th 87.0% | 16th 82.5% | 8th 85.5% | 5th 87.0% | 12th 83.5% | 14th 83.0% | |
| 74.0% | 75% | 81% | 67% | 67% | 78% | 70% | 73% | 76% | 72% | 69% | 87% | 72% | 77% | 92% | 60% | 69% | 70% | 70% | 83% | 77% | 69% | |
| 86.0% | 83% | 89% | 80% | 95% | 87% | 84% | 87% | 78% | 79% | 88% | 90% | 87% | 90% | 86% | 83% | 85% | 89% | 94% | 87% | 83% | 81% | |
| 83.4% | 84% | 86% | 83% | 83% | 86% | 78% | 77% | 76% | 82% | 87% | 77% | 77% | 85% | 78% | 90% | 95% | 82% | 89% | 84% | 82% | 90% | |
| 92.8% | 94% | 94% | 91% | 93% | 92% | 90% | 96% | 86% | 96% | 98% | 96% | 86% | 97% | 87% | 98% | 99% | 89% | 89% | 94% | 92% | 92% |