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 GD2 (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 85.0% | 15th 66.0% | 7th 75.7% | 6th 76.0% | 8th 71.7% | 19th 63.0% | 3rd 84.0% | 10th 70.3% | 14th 66.7% | 11th 69.3% | 16th 65.7% | 21st 51.0% | 13th 67.0% | 20th 59.7% | 1st 85.3% | 5th 77.0% | 17th 64.7% | 12th 68.3% | 18th 64.0% | 9th 70.7% | 4th 80.0% | |
| 80.3% | 95% | 85% | 92% | 90% | 73% | 75% | 93% | 93% | 84% | 88% | 76% | 57% | 77% | 71% | 80% | 86% | 68% | 71% | 75% | 79% | 79% | |
| 63.2% | 60% | 67% | 78% | 69% | 42% | 63% | 59% | 64% | 62% | 60% | 66% | 37% | 57% | 57% | 76% | 73% | 61% | 75% | 66% | 74% | 61% | |
| 68.0% | 100% | 46% | 57% | 69% | 100% | 51% | 100% | 54% | 54% | 60% | 55% | 59% | 67% | 51% | 100% | 72% | 65% | 59% | 51% | 59% | 100% |