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 | 3rd 86.3% | 8th 79.8% | 12th 78.0% | 15th 76.3% | 6th 82.3% | 13th 77.3% | 4th 83.0% | 20th 68.3% | 16th 75.8% | 7th 80.0% | 16th 75.8% | 21st 61.5% | 14th 76.8% | 11th 78.3% | 1st 91.5% | 5th 82.7% | 9th 79.0% | 19th 75.0% | 10th 78.8% | 18th 75.3% | 2nd 90.0% | |
| 56.0% | 100% | 50% | 44% | 39% | 63% | 48% | 67% | 30% | 44% | 55% | 39% | 44% | 48% | 43% | 100% | 68% | 46% | 59% | 46% | 44% | 100% | |
| 84.9% | 88% | 87% | 92% | 93% | 90% | 78% | 95% | 85% | 80% | 91% | 91% | 50% | 86% | 94% | 87% | 85% | 85% | 80% | 80% | 80% | 85% | |
| 82.0% | 76% | 85% | 86% | 87% | 95% | 95% | 75% | 72% | 84% | 86% | 74% | 56% | 79% | 78% | 84% | 81% | 86% | 79% | 95% | 88% | 81% | |
| 91.6% | 81% | 97% | 90% | 86% | 81% | 88% | 95% | 86% | 95% | 88% | 99% | 96% | 94% | 98% | 95% | 97% | 99% | 82% | 94% | 89% | 94% |