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 | 13th 74.5% | 2nd 84.0% | 8th 76.8% | 5th 77.5% | 1st 84.5% | 5th 77.5% | 15th 73.8% | 20th 70.2% | 14th 74.3% | 21st 68.5% | 3rd 83.5% | 11th 74.8% | 9th 75.3% | 10th 75.0% | 11th 74.8% | 4th 79.0% | 17th 72.5% | 16th 73.3% | 7th 77.0% | 19th 70.7% | 18th 71.5% | |
| 75.4% | 75% | 84% | 66% | 68% | 84% | 73% | 76% | 82% | 74% | 70% | 89% | 91% | 78% | 73% | 64% | 75% | 72% | 70% | 78% | 68% | 74% | |
| 80.3% | 70% | 86% | 86% | 84% | 88% | 86% | 83% | 68% | 74% | 71% | 93% | 58% | 85% | 81% | 78% | 84% | 85% | 81% | 86% | 80% | 80% | |
| 61.9% | 64% | 75% | 64% | 67% | 75% | 60% | 59% | 51% | 63% | 60% | 56% | 62% | 59% | 56% | 71% | 68% | 53% | 56% | 64% | 53% | 64% | |
| 85.0% | 89% | 91% | 91% | 91% | 91% | 91% | 77% | 80% | 86% | 73% | 96% | 88% | 79% | 90% | 86% | 89% | 80% | 86% | 80% | 82% | 68% |