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 | 10th 74.7% | 2nd 77.3% | 7th 76.0% | 8th 75.3% | 1st 80.7% | 12th 72.3% | 16th 71.0% | 4th 76.7% | 5th 76.3% | 12th 72.3% | 11th 73.7% | 17th 69.3% | 18th 68.3% | 6th 76.0% | 9th 75.0% | 3rd 76.7% | 20th 65.7% | 19th 66.0% | 15th 72.0% | 21st 64.7% | 12th 72.3% | |
| 89.7% | 89% | 91% | 94% | 91% | 91% | 86% | 85% | 97% | 94% | 89% | 94% | 91% | 86% | 94% | 91% | 91% | 86% | 91% | 90% | 80% | 82% | |
| 70.0% | 72% | 75% | 76% | 80% | 84% | 77% | 70% | 76% | 76% | 72% | 65% | 58% | 57% | 58% | 84% | 79% | 61% | 52% | 62% | 63% | 72% | |
| 59.3% | 63% | 66% | 58% | 55% | 67% | 54% | 58% | 57% | 59% | 56% | 62% | 59% | 62% | 76% | 50% | 60% | 50% | 55% | 64% | 51% | 63% |