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 56-65. 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 | 12th 75.8% | 1st 83.5% | 11th 76.8% | 13th 74.8% | 3rd 80.8% | 9th 77.0% | 18th 71.0% | 20th 70.0% | 14th 74.5% | 21st 68.3% | 4th 80.5% | 7th 77.8% | 9th 77.0% | 8th 77.3% | 14th 74.5% | 5th 79.0% | 17th 72.7% | 2nd 81.7% | 6th 78.3% | 16th 73.8% | 18th 71.0% | |
| 75.8% | 77% | 84% | 66% | 68% | 84% | 73% | 76% | 82% | 74% | 70% | 89% | 90% | 76% | 73% | 67% | 76% | 72% | 70% | 83% | 68% | 73% | |
| 80.8% | 70% | 86% | 86% | 84% | 81% | 86% | 72% | 67% | 74% | 71% | 86% | 79% | 90% | 83% | 81% | 83% | 85% | 83% | 86% | 83% | 80% | |
| 62.7% | 68% | 73% | 64% | 67% | 67% | 64% | 59% | 51% | 64% | 59% | 56% | 62% | 62% | 63% | 71% | 69% | 53% | 64% | 58% | 61% | ||
| 83.8% | 88% | 91% | 91% | 80% | 91% | 85% | 77% | 80% | 86% | 73% | 91% | 80% | 80% | 90% | 79% | 88% | 81% | 92% | 80% | 86% | 70% |