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 Equally concerned and 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 | 1st 82.8% | 3rd 78.0% | 9th 72.0% | 10th 71.8% | 7th 72.7% | 8th 72.3% | 12th 69.2% | 21st 61.5% | 16th 66.8% | 18th 64.5% | 15th 67.0% | 13th 68.8% | 17th 65.0% | 14th 67.5% | 6th 73.0% | 4th 75.3% | 11th 71.2% | 20th 62.0% | 5th 73.5% | 19th 62.3% | 2nd 79.5% | |
| 54.5% | 100% | 61% | 46% | 53% | 59% | 44% | 58% | 37% | 44% | 55% | 37% | 41% | 51% | 44% | 75% | 63% | 59% | 22% | 59% | 37% | 100% | |
| 78.0% | 78% | 84% | 89% | 75% | 83% | 80% | 80% | 72% | 77% | 72% | 83% | 81% | 78% | 81% | 72% | 80% | 75% | 73% | 78% | 74% | 72% | |
| 67.8% | 74% | 74% | 74% | 76% | 72% | 76% | 59% | 58% | 67% | 61% | 62% | 70% | 56% | 62% | 69% | 77% | 72% | 63% | 72% | 64% | 66% | |
| 81.0% | 79% | 93% | 79% | 83% | 77% | 89% | 80% | 79% | 79% | 70% | 86% | 83% | 75% | 83% | 76% | 81% | 79% | 90% | 85% | 74% | 80% |