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 26-35. 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 | 2nd 79.8% | 1st 81.8% | 5th 78.8% | 10th 77.8% | 7th 78.3% | 4th 79.0% | 8th 78.3% | 21st 69.5% | 15th 76.5% | 11th 77.3% | 8th 78.3% | 12th 77.0% | 16th 76.0% | 19th 74.5% | 16th 76.0% | 3rd 79.2% | 18th 75.5% | 12th 77.0% | 6th 78.5% | 20th 70.0% | 14th 76.5% | |
| 76.3% | 77% | 79% | 75% | 72% | 75% | 75% | 82% | 77% | 75% | 83% | 75% | 78% | 80% | 84% | 69% | 70% | 75% | 77% | 74% | 69% | 81% | |
| 78.4% | 82% | 84% | 84% | 73% | 83% | 78% | 81% | 69% | 76% | 74% | 84% | 82% | 79% | 76% | 76% | 83% | 77% | 81% | 78% | 72% | 75% | |
| 68.5% | 71% | 74% | 75% | 76% | 70% | 76% | 71% | 50% | 68% | 69% | 64% | 70% | 64% | 58% | 72% | 78% | 66% | 61% | 72% | 62% | 72% | |
| 84.4% | 89% | 90% | 81% | 90% | 85% | 87% | 79% | 82% | 87% | 83% | 90% | 78% | 81% | 80% | 87% | 86% | 84% | 89% | 90% | 77% | 78% |