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 | 2nd 86.3% | 3rd 81.3% | 5th 79.7% | 9th 78.0% | 10th 77.0% | 10th 77.0% | 1st 95.3% | 4th 80.8% | 18th 72.5% | 14th 76.5% | 6th 79.5% | 7th 78.8% | 13th 76.5% | 20th 69.8% | 15th 75.8% | 8th 78.5% | 16th 74.3% | 19th 70.8% | 21st 3.3% | 10th 77.0% | 17th 73.0% | |
| 51.2% | 100% | 43% | 50% | 44% | 59% | 48% | 100% | 63% | 37% | 44% | 44% | 55% | 44% | 44% | 44% | 43% | 41% | 33% | 43% | 44% | ||
| 82.4% | 84% | 91% | 86% | 92% | 87% | 79% | 97% | 90% | 88% | 83% | 85% | 86% | 89% | 81% | 87% | 95% | 82% | 87% | 0% | 81% | 80% | |
| 78.3% | 81% | 95% | 86% | 86% | 91% | 93% | 86% | 75% | 77% | 84% | 95% | 82% | 75% | 56% | 78% | 78% | 75% | 78% | 0% | 90% | 83% | |
| 87.9% | 80% | 96% | 97% | 90% | 71% | 88% | 98% | 95% | 88% | 95% | 94% | 92% | 98% | 98% | 94% | 98% | 99% | 85% | 10% | 94% | 85% |