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 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 88.7% | 4th 75.7% | 13th 66.3% | 6th 73.0% | 5th 74.0% | 9th 68.3% | 8th 69.3% | 19th 59.7% | 15th 66.0% | 11th 67.0% | 17th 62.3% | 10th 67.7% | 18th 60.3% | 13th 66.3% | 1st 90.3% | 7th 72.0% | 12th 66.7% | 20th 57.3% | 16th 64.0% | 21st 57.0% | 3rd 86.7% | |
| 84.5% | 92% | 90% | 80% | 86% | 80% | 85% | 87% | 83% | 84% | 76% | 87% | 87% | 81% | 86% | 83% | 83% | 87% | 94% | 80% | 77% | 86% | |
| 70.1% | 74% | 76% | 75% | 80% | 75% | 76% | 59% | 59% | 70% | 67% | 63% | 72% | 56% | 62% | 88% | 80% | 65% | 60% | 71% | 74% | ||
| 54.4% | 100% | 61% | 44% | 53% | 67% | 44% | 62% | 37% | 44% | 58% | 37% | 44% | 44% | 51% | 100% | 53% | 48% | 18% | 41% | 37% | 100% |