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 | 2nd 86.8% | 11th 77.5% | 8th 80.3% | 6th 83.5% | 20th 69.0% | 12th 77.0% | 5th 83.5% | 13th 76.8% | 7th 81.5% | 8th 80.3% | 15th 75.5% | 19th 72.7% | 14th 75.8% | 17th 74.8% | 4th 83.7% | 1st 89.3% | 18th 74.0% | 16th 75.0% | 10th 77.5% | 21st 63.7% | 3rd 84.8% | |
| 68.5% | 100% | 54% | 57% | 69% | 75% | 51% | 100% | 55% | 53% | 64% | 56% | 100% | 64% | 54% | 75% | 100% | 57% | 59% | 48% | 48% | 100% | |
| 86.1% | 90% | 83% | 91% | 99% | 81% | 87% | 90% | 95% | 97% | 96% | 87% | 67% | 80% | 93% | 88% | 91% | 76% | 82% | 91% | 64% | 80% | |
| 68.3% | 74% | 76% | 76% | 76% | 57% | 76% | 55% | 68% | 77% | 73% | 62% | 38% | 63% | 58% | 76% | 75% | 72% | 72% | 78% | 63% | 70% | |
| 90.0% | 83% | 97% | 97% | 90% | 63% | 94% | 89% | 89% | 99% | 88% | 97% | 86% | 96% | 94% | 96% | 91% | 91% | 87% | 93% | 80% | 89% |