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 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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 5th 78.3% | 5th 78.3% | 13th 75.0% | 7th 76.3% | 4th 79.3% | 18th 72.3% | 17th 73.7% | 18th 72.3% | 12th 75.3% | 14th 74.7% | 2nd 80.7% | 16th 74.0% | 21st 71.0% | 7th 76.3% | 20th 71.7% | 14th 74.7% | 10th 76.0% | 7th 76.3% | 2nd 80.7% | 10th 76.0% | 1st 81.3% | |
| 88.9% | 91% | 90% | 84% | 91% | 92% | 83% | 93% | 82% | 94% | 89% | 93% | 95% | 87% | 90% | 90% | 87% | 82% | 86% | 92% | 90% | 86% | |
| 72.3% | 77% | 77% | 83% | 80% | 77% | 73% | 67% | 63% | 70% | 77% | 73% | 58% | 65% | 61% | 77% | 79% | 76% | 72% | 76% | 64% | 73% | |
| 66.6% | 67% | 68% | 58% | 58% | 69% | 61% | 61% | 72% | 62% | 58% | 76% | 69% | 61% | 78% | 48% | 58% | 70% | 71% | 74% | 74% | 85% |