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 | 15th 81.3% | 10th 84.3% | 4th 88.0% | 17th 79.8% | 19th 79.3% | 17th 79.8% | 1st 90.8% | 11th 83.8% | 21st 77.3% | 16th 80.8% | 2nd 88.5% | 8th 85.0% | 2nd 88.5% | 9th 84.7% | 5th 87.8% | 13th 82.8% | 12th 83.0% | 20th 79.0% | 14th 82.7% | 6th 87.3% | 7th 87.0% | |
| 78.0% | 71% | 80% | 76% | 66% | 75% | 66% | 85% | 75% | 79% | 73% | 85% | 73% | 83% | 84% | 87% | 89% | 75% | 61% | 87% | 79% | 89% | |
| 86.8% | 84% | 88% | 94% | 83% | 77% | 81% | 94% | 91% | 80% | 83% | 93% | 92% | 89% | 88% | 91% | 85% | 85% | 87% | 81% | 89% | 87% | |
| 78.3% | 75% | 78% | 84% | 79% | 85% | 79% | 86% | 75% | 68% | 76% | 79% | 82% | 82% | 75% | 73% | 72% | 80% | 75% | 80% | 87% | 75% | |
| 92.8% | 95% | 91% | 98% | 91% | 80% | 93% | 98% | 94% | 82% | 91% | 97% | 93% | 100% | 92% | 100% | 85% | 92% | 93% | 94% | 97% |