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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 85.8% | 9th 80.8% | 10th 79.8% | 11th 79.0% | 14th 77.0% | 18th 73.0% | 2nd 88.0% | 5th 83.0% | 20th 70.3% | 15th 75.0% | 6th 82.8% | 7th 81.3% | 16th 74.5% | 21st 67.3% | 17th 73.5% | 13th 78.0% | 8th 81.0% | 19th 71.8% | 1st 89.7% | 12th 78.0% | 4th 85.0% | |
| 51.2% | 100% | 43% | 50% | 44% | 59% | 48% | 71% | 67% | 37% | 44% | 56% | 56% | 37% | 41% | 44% | 41% | 62% | 30% | 43% | |||
| 85.9% | 89% | 89% | 87% | 92% | 86% | 78% | 96% | 95% | 86% | 78% | 86% | 89% | 89% | 63% | 85% | 95% | 84% | 78% | 92% | 86% | 80% | |
| 81.5% | 73% | 95% | 85% | 90% | 83% | 78% | 88% | 75% | 73% | 83% | 95% | 87% | 73% | 69% | 71% | 78% | 79% | 85% | 80% | 89% | 83% | |
| 93.0% | 81% | 96% | 97% | 90% | 80% | 88% | 97% | 95% | 85% | 95% | 94% | 93% | 99% | 96% | 94% | 98% | 99% | 94% | 97% | 94% | 92% |