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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 18th 82.0% | 6th 86.5% | 19th 80.0% | 12th 84.5% | 14th 83.7% | 16th 82.3% | 15th 83.5% | 21st 76.5% | 16th 82.3% | 11th 85.2% | 2nd 87.8% | 20th 80.0% | 3rd 87.5% | 8th 85.8% | 4th 87.3% | 8th 85.8% | 7th 86.0% | 4th 87.3% | 10th 85.3% | 13th 84.0% | 1st 89.8% | |
| 76.0% | 74% | 77% | 66% | 67% | 78% | 70% | 73% | 72% | 73% | 69% | 87% | 86% | 84% | 92% | 73% | 77% | 78% | 71% | 79% | 70% | 81% | |
| 86.7% | 79% | 89% | 80% | 95% | 87% | 84% | 89% | 78% | 79% | 90% | 91% | 86% | 87% | 86% | 92% | 82% | 92% | 94% | 87% | 81% | 93% | |
| 82.3% | 80% | 86% | 83% | 83% | 86% | 85% | 76% | 74% | 82% | 84% | 77% | 62% | 84% | 77% | 88% | 88% | 80% | 92% | 86% | 87% | 89% | |
| 92.6% | 95% | 94% | 91% | 93% | 84% | 90% | 96% | 82% | 95% | 98% | 96% | 86% | 95% | 88% | 96% | 96% | 94% | 92% | 89% | 98% | 96% |