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 46-55. 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 | 18th 76.0% | 7th 81.5% | 6th 81.5% | 21st 74.0% | 13th 79.5% | 9th 80.5% | 3rd 83.5% | 14th 78.8% | 17th 77.0% | 16th 77.3% | 10th 80.3% | 19th 75.5% | 1st 84.5% | 15th 78.0% | 11th 79.8% | 5th 82.5% | 12th 79.5% | 7th 81.5% | 4th 82.5% | 2nd 83.8% | 20th 75.3% | |
| 80.7% | 73% | 86% | 78% | 68% | 78% | 70% | 87% | 77% | 85% | 73% | 89% | 72% | 85% | 78% | 85% | 87% | 84% | 83% | 91% | 85% | 80% | |
| 77.4% | 69% | 84% | 82% | 69% | 72% | 82% | 84% | 81% | 71% | 74% | 80% | 72% | 86% | 74% | 78% | 82% | 74% | 83% | 75% | 81% | 73% | |
| 75.1% | 77% | 74% | 80% | 75% | 80% | 80% | 76% | 72% | 67% | 76% | 69% | 78% | 80% | 72% | 74% | 73% | 71% | 78% | 74% | 79% | 73% | |
| 85.3% | 85% | 82% | 86% | 84% | 88% | 90% | 87% | 85% | 85% | 86% | 83% | 80% | 87% | 88% | 82% | 88% | 89% | 82% | 90% | 90% | 75% |