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 Equally concerned and excited. 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 | 2nd 87.0% | 12th 71.7% | 10th 72.3% | 14th 71.0% | 9th 73.0% | 12th 71.7% | 4th 79.3% | 21st 63.3% | 10th 72.3% | 7th 76.0% | 15th 70.0% | 19th 64.0% | 16th 69.0% | 18th 65.7% | 3rd 80.0% | 4th 79.3% | 20th 63.7% | 17th 65.7% | 6th 77.3% | 8th 73.3% | 1st 90.7% | |
| 89.5% | 86% | 84% | 97% | 92% | 89% | 77% | 95% | 78% | 94% | 98% | 99% | 82% | 92% | 86% | 95% | 95% | 84% | 86% | 92% | 87% | 92% | |
| 77.1% | 75% | 81% | 76% | 76% | 78% | 90% | 75% | 73% | 79% | 78% | 74% | 73% | 64% | 67% | 73% | 79% | 80% | 78% | 92% | 79% | 80% | |
| 52.8% | 100% | 50% | 44% | 45% | 52% | 48% | 68% | 39% | 44% | 52% | 37% | 37% | 51% | 44% | 72% | 64% | 27% | 33% | 48% | 54% | 100% |