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 85.8% | 8th 79.8% | 9th 79.0% | 13th 76.3% | 12th 77.0% | 18th 73.0% | 5th 83.0% | 20th 70.3% | 14th 75.0% | 6th 81.3% | 16th 74.5% | 21st 67.3% | 17th 73.5% | 11th 78.0% | 3rd 85.0% | 4th 85.0% | 7th 81.0% | 19th 71.8% | 10th 78.0% | 15th 74.8% | 1st 88.5% | |
| 53.9% | 100% | 50% | 44% | 39% | 59% | 48% | 67% | 37% | 44% | 56% | 37% | 41% | 44% | 41% | 67% | 78% | 62% | 30% | 43% | 44% | 100% | |
| 85.3% | 89% | 87% | 92% | 93% | 86% | 78% | 95% | 86% | 78% | 89% | 89% | 63% | 85% | 95% | 89% | 85% | 84% | 78% | 86% | 80% | 85% | |
| 80.8% | 73% | 85% | 90% | 87% | 83% | 78% | 75% | 73% | 83% | 87% | 73% | 69% | 71% | 78% | 87% | 85% | 79% | 85% | 89% | 83% | 84% | |
| 91.9% | 81% | 97% | 90% | 86% | 80% | 88% | 95% | 85% | 95% | 93% | 99% | 96% | 94% | 98% | 97% | 92% | 99% | 94% | 94% | 92% | 85% |