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 | 2nd 82.5% | 4th 78.0% | 10th 71.5% | 8th 72.8% | 6th 73.8% | 9th 72.3% | 11th 69.8% | 21st 61.7% | 17th 66.0% | 14th 68.3% | 16th 67.0% | 12th 68.8% | 19th 64.0% | 15th 67.8% | 1st 84.5% | 5th 75.8% | 13th 68.5% | 18th 65.5% | 7th 73.5% | 20th 63.8% | 3rd 80.5% | |
| 55.4% | 100% | 61% | 46% | 54% | 59% | 44% | 61% | 37% | 44% | 55% | 37% | 41% | 44% | 44% | 100% | 60% | 48% | 33% | 59% | 37% | 100% | |
| 78.4% | 74% | 84% | 89% | 78% | 81% | 80% | 80% | 72% | 74% | 78% | 83% | 81% | 78% | 82% | 77% | 80% | 75% | 78% | 79% | 71% | 72% | |
| 68.7% | 74% | 74% | 74% | 76% | 72% | 76% | 59% | 58% | 67% | 62% | 62% | 70% | 56% | 62% | 80% | 76% | 72% | 61% | 71% | 68% | 72% | |
| 82.5% | 82% | 93% | 77% | 83% | 83% | 89% | 79% | 80% | 79% | 78% | 86% | 83% | 78% | 83% | 81% | 87% | 79% | 90% | 85% | 79% | 78% |