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 | 13th 83.3% | 3rd 87.5% | 18th 81.5% | 9th 84.5% | 5th 87.0% | 16th 82.5% | 15th 83.0% | 21st 78.0% | 17th 81.7% | 10th 84.5% | 4th 87.3% | 20th 78.8% | 1st 88.8% | 8th 85.8% | 11th 84.3% | 7th 86.0% | 19th 80.5% | 14th 83.0% | 6th 86.5% | 12th 83.8% | 1st 88.8% | |
| 76.5% | 81% | 81% | 66% | 67% | 81% | 70% | 73% | 75% | 71% | 71% | 90% | 79% | 84% | 92% | 66% | 76% | 70% | 74% | 80% | 79% | 81% | |
| 85.0% | 77% | 89% | 80% | 95% | 87% | 84% | 86% | 78% | 79% | 84% | 86% | 86% | 90% | 86% | 82% | 85% | 88% | 81% | 88% | 81% | 92% | |
| 81.8% | 80% | 86% | 89% | 83% | 89% | 86% | 77% | 71% | 82% | 86% | 77% | 63% | 86% | 77% | 90% | 88% | 77% | 84% | 84% | 77% | 86% | |
| 93.2% | 95% | 94% | 91% | 93% | 91% | 90% | 96% | 88% | 95% | 97% | 96% | 87% | 95% | 88% | 99% | 95% | 87% | 93% | 94% | 98% | 96% |