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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 18th 82.0% | 4th 87.5% | 7th 86.5% | 19th 80.0% | 13th 83.7% | 16th 82.3% | 1st 88.8% | 14th 83.5% | 21st 76.5% | 16th 82.3% | 2nd 88.5% | 11th 85.2% | 3rd 87.8% | 20th 80.0% | 4th 87.5% | 9th 85.8% | 8th 86.0% | 6th 87.3% | 14th 83.5% | 10th 85.3% | 12th 84.0% | |
| 78.8% | 74% | 86% | 77% | 66% | 78% | 70% | 87% | 73% | 72% | 73% | 91% | 69% | 87% | 86% | 84% | 92% | 78% | 71% | 91% | 79% | 70% | |
| 85.9% | 79% | 90% | 89% | 80% | 87% | 84% | 91% | 89% | 78% | 79% | 86% | 90% | 91% | 86% | 87% | 86% | 92% | 94% | 78% | 87% | 81% | |
| 81.1% | 80% | 79% | 86% | 83% | 86% | 85% | 84% | 76% | 74% | 82% | 83% | 84% | 77% | 62% | 84% | 77% | 80% | 92% | 77% | 86% | 87% | |
| 92.0% | 95% | 95% | 94% | 91% | 84% | 90% | 93% | 96% | 82% | 95% | 94% | 98% | 96% | 86% | 95% | 88% | 94% | 92% | 88% | 89% | 98% |