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 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 | 16th 76.0% | 4th 81.5% | 20th 74.0% | 17th 75.5% | 10th 79.5% | 6th 80.5% | 11th 78.8% | 15th 77.0% | 14th 77.3% | 17th 75.5% | 1st 84.5% | 13th 78.0% | 7th 79.8% | 3rd 82.5% | 21st 73.8% | 7th 79.8% | 9th 79.5% | 5th 81.5% | 2nd 83.8% | 19th 75.3% | 12th 78.3% | |
| 77.0% | 73% | 78% | 68% | 65% | 78% | 70% | 77% | 85% | 73% | 72% | 85% | 78% | 85% | 87% | 59% | 74% | 84% | 83% | 85% | 80% | 79% | |
| 76.7% | 69% | 82% | 69% | 73% | 72% | 82% | 81% | 71% | 74% | 72% | 86% | 74% | 78% | 82% | 77% | 78% | 74% | 83% | 81% | 73% | 80% | |
| 76.5% | 77% | 80% | 75% | 80% | 80% | 80% | 72% | 67% | 76% | 78% | 80% | 72% | 74% | 73% | 82% | 81% | 71% | 78% | 79% | 73% | 78% | |
| 84.4% | 85% | 86% | 84% | 84% | 88% | 90% | 85% | 85% | 86% | 80% | 87% | 88% | 82% | 88% | 77% | 86% | 89% | 82% | 90% | 75% | 76% |