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 | 3rd 85.0% | 11th 78.3% | 10th 78.3% | 6th 83.5% | 21st 64.0% | 12th 76.3% | 5th 84.5% | 16th 75.0% | 8th 79.3% | 7th 80.8% | 13th 76.0% | 19th 72.0% | 15th 75.8% | 18th 73.0% | 2nd 90.8% | 1st 92.3% | 9th 78.5% | 20th 69.5% | 13th 76.0% | 17th 74.0% | 4th 85.0% | |
| 69.8% | 100% | 54% | 57% | 69% | 76% | 51% | 100% | 51% | 46% | 62% | 58% | 100% | 64% | 55% | 100% | 100% | 59% | 55% | 49% | 59% | 100% | |
| 88.5% | 89% | 86% | 91% | 99% | 72% | 87% | 93% | 91% | 99% | 96% | 88% | 67% | 80% | 92% | 94% | 99% | 98% | 80% | 88% | 89% | 80% | |
| 67.4% | 72% | 76% | 76% | 76% | 55% | 73% | 56% | 66% | 77% | 73% | 63% | 35% | 63% | 54% | 75% | 76% | 67% | 62% | 75% | 67% | 79% | |
| 88.1% | 79% | 97% | 89% | 90% | 53% | 94% | 89% | 92% | 95% | 92% | 95% | 86% | 96% | 91% | 94% | 94% | 90% | 81% | 92% | 81% | 81% |