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 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 | 1st 84.8% | 4th 78.8% | 9th 71.5% | 10th 71.0% | 7th 72.0% | 5th 72.3% | 11th 69.8% | 20th 62.0% | 16th 66.0% | 18th 65.0% | 15th 66.5% | 12th 68.3% | 17th 65.8% | 13th 67.8% | 2nd 82.0% | 5th 72.3% | 14th 66.8% | 21st 61.0% | 8th 71.5% | 19th 62.2% | 3rd 80.3% | |
| 53.7% | 100% | 61% | 46% | 50% | 59% | 44% | 61% | 37% | 44% | 53% | 37% | 33% | 51% | 44% | 84% | 54% | 48% | 18% | 59% | 44% | 100% | |
| 77.9% | 72% | 87% | 89% | 75% | 81% | 80% | 80% | 72% | 74% | 70% | 83% | 87% | 78% | 82% | 79% | 80% | 75% | 71% | 77% | 71% | 73% | |
| 68.0% | 74% | 74% | 74% | 76% | 72% | 76% | 59% | 60% | 67% | 62% | 63% | 70% | 56% | 62% | 82% | 72% | 58% | 69% | 72% | 63% | 68% | |
| 81.8% | 93% | 93% | 77% | 83% | 76% | 89% | 79% | 79% | 79% | 75% | 83% | 83% | 78% | 83% | 83% | 83% | 86% | 86% | 78% | 71% |