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 Female. 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 | 12th 84.3% | 5th 87.5% | 4th 88.0% | 18th 80.8% | 20th 78.0% | 19th 79.8% | 1st 89.8% | 13th 83.3% | 21st 77.0% | 16th 81.3% | 1st 89.8% | 9th 86.0% | 11th 84.5% | 14th 82.8% | 5th 87.5% | 10th 85.5% | 15th 82.0% | 16th 81.3% | 3rd 89.5% | 7th 87.3% | 8th 87.0% | |
| 78.9% | 73% | 86% | 76% | 70% | 75% | 66% | 82% | 75% | 77% | 76% | 89% | 71% | 79% | 83% | 84% | 89% | 80% | 76% | 88% | 78% | 83% | |
| 87.2% | 90% | 91% | 93% | 83% | 77% | 81% | 93% | 92% | 81% | 82% | 93% | 93% | 87% | 88% | 91% | 95% | 82% | 78% | 89% | 87% | 86% | |
| 79.2% | 78% | 77% | 85% | 79% | 79% | 79% | 89% | 75% | 68% | 76% | 80% | 87% | 74% | 75% | 77% | 73% | 76% | 81% | 86% | 88% | 82% | |
| 92.3% | 96% | 96% | 98% | 91% | 81% | 93% | 95% | 91% | 82% | 91% | 97% | 93% | 98% | 85% | 98% | 85% | 90% | 90% | 95% | 96% | 97% |