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 18-25. 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 Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT 5 | GPT 5.1 | GPT OSS 120b | GPT OSS 20b | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | Grok 4 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 1st 80.0% | 3rd 79.5% | 7th 77.5% | 8th 77.3% | 2nd 79.5% | 10th 75.8% | 16th 73.8% | 20th 70.5% | 18th 73.3% | 12th 74.5% | 11th 75.3% | 4th 79.0% | 15th 74.0% | 19th 71.7% | 5th 78.5% | 6th 78.5% | 14th 74.3% | 17th 73.5% | 9th 76.0% | 21st 68.8% | 12th 74.5% | |
| 78.0% | 78% | 79% | 77% | 79% | 77% | 78% | 79% | 80% | 76% | 81% | 73% | 81% | 81% | 82% | 79% | 79% | 76% | 76% | 75% | 71% | 82% | |
| 77.6% | 83% | 76% | 84% | 76% | 85% | 77% | 81% | 69% | 78% | 75% | 82% | 82% | 78% | 71% | 83% | 77% | 75% | 71% | 76% | 71% | 80% | |
| 66.5% | 70% | 75% | 75% | 77% | 77% | 60% | 59% | 51% | 58% | 62% | 64% | 72% | 58% | 57% | 74% | 75% | 72% | 61% | 71% | 64% | 64% | |
| 79.9% | 89% | 88% | 74% | 77% | 79% | 88% | 76% | 82% | 81% | 80% | 82% | 81% | 79% | 77% | 78% | 83% | 74% | 86% | 82% | 69% | 72% |