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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 76.7% | 2nd 77.3% | 8th 74.3% | 6th 75.3% | 1st 81.7% | 11th 72.3% | 14th 71.3% | 17th 69.7% | 4th 76.3% | 12th 71.7% | 10th 73.7% | 18th 69.0% | 15th 70.0% | 9th 74.3% | 7th 75.0% | 5th 75.3% | 20th 59.3% | 19th 67.3% | 13th 71.3% | 15th 70.0% | |
| 90.1% | 85% | 91% | 89% | 91% | 94% | 86% | 85% | 94% | 94% | 89% | 94% | 91% | 91% | 94% | 94% | 91% | 82% | 92% | 90% | 86% | |
| 68.5% | 83% | 75% | 76% | 80% | 84% | 77% | 70% | 58% | 76% | 73% | 65% | 57% | 57% | 57% | 84% | 77% | 45% | 52% | 60% | 63% | |
| 59.2% | 62% | 66% | 58% | 55% | 67% | 54% | 59% | 57% | 59% | 53% | 62% | 59% | 62% | 72% | 47% | 58% | 51% | 58% | 64% | 61% |