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 Male. 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 | 20th 80.0% | 4th 86.5% | 8th 85.5% | 17th 82.0% | 18th 81.3% | 9th 84.7% | 2nd 87.0% | 13th 83.7% | 21st 77.5% | 11th 84.5% | 12th 83.8% | 5th 86.0% | 6th 86.0% | 19th 80.7% | 6th 86.0% | 15th 82.3% | 1st 87.3% | 14th 83.3% | 15th 82.3% | 3rd 86.8% | 10th 84.5% | |
| 78.7% | 76% | 83% | 78% | 71% | 76% | 71% | 80% | 79% | 77% | 83% | 73% | 77% | 84% | 82% | 83% | 88% | 79% | 74% | 81% | 80% | 78% | |
| 81.4% | 65% | 86% | 83% | 76% | 79% | 92% | 84% | 84% | 70% | 73% | 87% | 83% | 84% | 84% | 82% | 82% | 88% | 94% | 71% | 81% | 82% | |
| 82.3% | 85% | 79% | 91% | 91% | 82% | 82% | 88% | 80% | 68% | 86% | 81% | 87% | 76% | 73% | 81% | 76% | 84% | 76% | 81% | 90% | 91% | |
| 93.1% | 94% | 98% | 90% | 90% | 88% | 94% | 96% | 92% | 95% | 96% | 94% | 97% | 100% | 84% | 98% | 83% | 98% | 89% | 96% | 96% | 87% |