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 | 19th 75.5% | 7th 79.8% | 21st 74.0% | 20th 75.5% | 14th 77.8% | 12th 78.8% | 12th 78.8% | 15th 76.3% | 16th 76.0% | 18th 75.8% | 1st 82.3% | 11th 79.0% | 6th 80.3% | 4th 81.5% | 16th 76.0% | 8th 79.5% | 10th 79.3% | 1st 82.3% | 3rd 82.0% | 5th 80.5% | 8th 79.5% | |
| 77.1% | 71% | 78% | 68% | 65% | 79% | 71% | 77% | 85% | 73% | 69% | 85% | 82% | 83% | 87% | 63% | 75% | 83% | 80% | 85% | 81% | 79% | |
| 76.4% | 71% | 75% | 69% | 73% | 72% | 82% | 81% | 71% | 70% | 74% | 82% | 74% | 77% | 79% | 76% | 79% | 78% | 84% | 75% | 77% | 86% | |
| 76.1% | 73% | 80% | 75% | 80% | 72% | 72% | 72% | 66% | 77% | 77% | 75% | 72% | 78% | 72% | 84% | 82% | 73% | 82% | 78% | 82% | 77% | |
| 84.6% | 87% | 86% | 84% | 84% | 88% | 90% | 85% | 83% | 84% | 83% | 87% | 88% | 83% | 88% | 81% | 82% | 83% | 83% | 90% | 82% | 76% |