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 | 10th 83.8% | 3rd 87.5% | 18th 80.0% | 12th 83.5% | 5th 87.0% | 17th 82.5% | 14th 83.3% | 21st 77.8% | 11th 83.7% | 7th 86.3% | 2nd 89.0% | 20th 79.3% | 8th 85.5% | 8th 85.5% | 13th 83.5% | 6th 86.5% | 19th 80.0% | 14th 83.3% | 4th 87.3% | 14th 83.3% | 1st 89.8% | |
| 76.1% | 77% | 81% | 66% | 67% | 81% | 70% | 73% | 75% | 73% | 71% | 90% | 83% | 77% | 92% | 67% | 76% | 82% | 64% | 82% | 70% | 81% | |
| 86.1% | 79% | 89% | 80% | 91% | 87% | 84% | 87% | 78% | 85% | 90% | 90% | 86% | 88% | 86% | 84% | 85% | 86% | 93% | 87% | 81% | 93% | |
| 81.3% | 83% | 86% | 83% | 83% | 86% | 86% | 77% | 72% | 82% | 87% | 78% | 62% | 82% | 78% | 88% | 87% | 58% | 84% | 86% | 90% | 89% | |
| 93.2% | 96% | 94% | 91% | 93% | 94% | 90% | 96% | 86% | 95% | 97% | 98% | 86% | 95% | 86% | 95% | 98% | 94% | 92% | 94% | 92% | 96% |