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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 1st 87.3% | 5th 77.0% | 6th 74.3% | 3rd 81.0% | 10th 70.7% | 9th 72.0% | 8th 72.7% | 17th 67.0% | 14th 69.3% | 16th 68.3% | 11th 70.0% | 18th 66.0% | 20th 63.7% | 7th 74.0% | 2nd 86.0% | 4th 80.3% | 11th 70.0% | 21st 63.3% | 13th 69.7% | 19th 65.7% | 15th 69.0% | |
| 89.6% | 96% | 95% | 95% | 95% | 76% | 92% | 94% | 97% | 97% | 84% | 93% | 76% | 85% | 93% | 86% | 94% | 92% | 91% | 95% | 79% | 76% | |
| 60.5% | 66% | 78% | 71% | 80% | 59% | 63% | 61% | 50% | 57% | 58% | 54% | 59% | 47% | 62% | 72% | 75% | 55% | 40% | 56% | 59% | 49% | |
| 66.7% | 100% | 58% | 57% | 68% | 77% | 61% | 63% | 54% | 54% | 63% | 63% | 63% | 59% | 67% | 100% | 72% | 63% | 59% | 58% | 59% | 82% |