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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 1st 89.0% | 12th 71.7% | 17th 69.7% | 14th 71.0% | 14th 71.0% | 9th 75.3% | 5th 77.3% | 18th 67.7% | 12th 71.7% | 11th 73.0% | 14th 71.0% | 20th 65.3% | 19th 67.3% | 21st 64.7% | 3rd 82.7% | 6th 76.3% | 8th 75.7% | 7th 76.0% | 4th 78.0% | 10th 74.0% | 2nd 87.0% | |
| 90.0% | 91% | 84% | 89% | 91% | 82% | 88% | 95% | 89% | 94% | 95% | 96% | 86% | 92% | 86% | 95% | 89% | 91% | 91% | 92% | 92% | 81% | |
| 76.0% | 76% | 81% | 76% | 76% | 76% | 90% | 76% | 71% | 77% | 72% | 73% | 73% | 59% | 67% | 76% | 74% | 77% | 78% | 92% | 76% | 80% | |
| 56.2% | 100% | 50% | 44% | 46% | 55% | 48% | 61% | 43% | 44% | 52% | 44% | 37% | 51% | 41% | 77% | 66% | 59% | 59% | 50% | 54% | 100% |