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 | 1st 90.0% | 5th 81.3% | 6th 80.0% | 9th 79.0% | 4th 81.5% | 11th 76.8% | 2nd 83.3% | 3rd 82.7% | 19th 71.0% | 17th 75.0% | 14th 76.3% | 7th 79.8% | 17th 75.0% | 21st 65.5% | 15th 76.0% | 11th 76.8% | 11th 76.8% | 10th 77.5% | 15th 76.0% | 8th 79.5% | 20th 68.3% | |
| 49.5% | 100% | 43% | 50% | 44% | 63% | 48% | 51% | 66% | 38% | 44% | 32% | 54% | 39% | 33% | 49% | 41% | 55% | 48% | 55% | 43% | 44% | |
| 86.3% | 81% | 91% | 88% | 92% | 93% | 78% | 96% | 95% | 86% | 83% | 85% | 87% | 89% | 81% | 87% | 95% | 83% | 80% | 82% | 86% | 75% | |
| 81.6% | 81% | 95% | 85% | 90% | 89% | 93% | 88% | 75% | 72% | 78% | 95% | 86% | 73% | 56% | 76% | 73% | 75% | 90% | 79% | 95% | 69% | |
| 92.6% | 98% | 96% | 97% | 90% | 81% | 88% | 98% | 95% | 88% | 95% | 93% | 92% | 99% | 92% | 92% | 98% | 94% | 92% | 88% | 94% | 85% |