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 | 1st 85.5% | 7th 72.8% | 11th 71.2% | 3rd 77.0% | 19th 64.5% | 12th 70.5% | 10th 72.0% | 13th 69.0% | 16th 67.5% | 19th 64.5% | 9th 72.5% | 7th 72.8% | 21st 61.7% | 5th 74.3% | 2nd 82.2% | 4th 76.8% | 17th 64.8% | 14th 68.0% | 15th 67.8% | 18th 64.8% | 6th 73.0% | |
| 66.4% | 100% | 56% | 57% | 68% | 73% | 53% | 59% | 54% | 51% | 62% | 63% | 63% | 58% | 71% | 100% | 72% | 55% | 58% | 58% | 63% | 100% | |
| 85.0% | 93% | 91% | 82% | 81% | 77% | 84% | 91% | 89% | 88% | 79% | 88% | 88% | 82% | 87% | 88% | 91% | 88% | 80% | 78% | 84% | 75% | |
| 56.9% | 63% | 61% | 66% | 76% | 50% | 58% | 55% | 50% | 54% | 51% | 52% | 52% | 46% | 52% | 72% | 73% | 49% | 62% | 54% | 44% | 54% | |
| 76.2% | 86% | 83% | 80% | 83% | 58% | 87% | 83% | 83% | 77% | 66% | 87% | 88% | 61% | 87% | 69% | 71% | 67% | 72% | 81% | 68% | 63% |