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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 85.2% | 5th 79.8% | 10th 78.0% | 13th 76.0% | 14th 75.8% | 11th 77.8% | 4th 81.8% | 20th 69.8% | 17th 75.0% | 7th 79.3% | 16th 75.3% | 21st 68.8% | 18th 74.8% | 15th 75.8% | 1st 89.8% | 2nd 85.8% | 9th 78.8% | 19th 70.5% | 6th 79.5% | 11th 77.8% | 8th 79.0% | |
| 52.6% | 100% | 50% | 44% | 39% | 51% | 48% | 66% | 30% | 44% | 53% | 41% | 41% | 54% | 41% | 100% | 78% | 56% | 30% | 43% | 44% | 51% | |
| 85.8% | 84% | 87% | 92% | 92% | 86% | 82% | 91% | 85% | 83% | 88% | 87% | 87% | 85% | 86% | 88% | 84% | 84% | 78% | 86% | 81% | 85% | |
| 80.0% | 75% | 85% | 86% | 87% | 87% | 93% | 75% | 72% | 78% | 84% | 74% | 51% | 63% | 78% | 75% | 84% | 76% | 87% | 95% | 90% | 84% | |
| 92.9% | 82% | 97% | 90% | 86% | 79% | 88% | 95% | 92% | 95% | 92% | 99% | 96% | 97% | 98% | 96% | 97% | 99% | 87% | 94% | 96% | 96% |