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 | 8th 79.3% | 12th 77.5% | 7th 80.3% | 5th 83.5% | 21st 65.0% | 11th 77.5% | 4th 83.5% | 10th 77.8% | 9th 78.8% | 6th 80.5% | 16th 74.0% | 19th 72.5% | 20th 71.8% | 17th 73.0% | 1st 91.5% | 3rd 85.3% | 14th 76.8% | 15th 74.5% | 13th 77.0% | 18th 73.0% | 2nd 88.3% | |
| 69.3% | 100% | 54% | 57% | 69% | 59% | 53% | 100% | 54% | 46% | 63% | 58% | 100% | 58% | 54% | 100% | 100% | 55% | 55% | 48% | 72% | 100% | |
| 87.2% | 89% | 83% | 91% | 99% | 72% | 87% | 90% | 95% | 97% | 99% | 88% | 67% | 80% | 93% | 95% | 86% | 88% | 86% | 91% | 75% | 80% | |
| 67.2% | 63% | 76% | 76% | 76% | 59% | 76% | 55% | 68% | 77% | 73% | 63% | 37% | 62% | 54% | 72% | 75% | 69% | 63% | 76% | 64% | 77% | |
| 88.9% | 65% | 97% | 97% | 90% | 70% | 94% | 89% | 94% | 95% | 87% | 87% | 86% | 87% | 91% | 99% | 80% | 95% | 94% | 93% | 81% | 96% |