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 More concerned than 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 | 4th 86.3% | 9th 77.7% | 11th 77.3% | 5th 83.5% | 21st 65.8% | 10th 77.5% | 17th 74.5% | 13th 76.3% | 8th 78.0% | 7th 81.2% | 14th 76.0% | 19th 72.0% | 15th 75.3% | 18th 72.8% | 2nd 90.5% | 1st 91.0% | 16th 74.5% | 6th 83.0% | 12th 76.5% | 20th 68.3% | 3rd 86.8% | |
| 67.0% | 100% | 52% | 57% | 69% | 59% | 53% | 63% | 51% | 46% | 62% | 58% | 100% | 66% | 54% | 100% | 100% | 51% | 57% | 49% | 59% | 100% | |
| 88.3% | 94% | 86% | 91% | 99% | 81% | 87% | 90% | 97% | 94% | 95% | 88% | 64% | 80% | 92% | 95% | 94% | 88% | 98% | 88% | 73% | 80% | |
| 69.5% | 75% | 76% | 76% | 76% | 58% | 76% | 56% | 71% | 77% | 74% | 63% | 38% | 64% | 54% | 75% | 76% | 72% | 86% | 76% | 62% | 78% | |
| 88.5% | 76% | 97% | 85% | 90% | 65% | 94% | 89% | 86% | 95% | 94% | 95% | 86% | 91% | 91% | 92% | 94% | 87% | 91% | 93% | 79% | 89% |