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 36-45. 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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 10th 82.0% | 3rd 84.5% | 20th 76.3% | 6th 83.3% | 21st 76.0% | 12th 81.5% | 14th 80.5% | 18th 76.5% | 19th 76.5% | 11th 81.8% | 1st 85.0% | 12th 81.5% | 7th 82.8% | 4th 84.0% | 15th 80.0% | 9th 82.3% | 16th 79.5% | 4th 84.0% | 2nd 84.5% | 16th 79.5% | 8th 82.5% | |
| 73.5% | 75% | 72% | 67% | 69% | 69% | 67% | 70% | 77% | 71% | 68% | 79% | 79% | 78% | 84% | 62% | 71% | 76% | 84% | 75% | 79% | 71% | |
| 84.6% | 80% | 91% | 71% | 89% | 77% | 92% | 89% | 73% | 71% | 86% | 91% | 86% | 89% | 84% | 83% | 87% | 84% | 90% | 89% | 82% | 92% | |
| 74.0% | 78% | 79% | 79% | 81% | 76% | 75% | 70% | 65% | 72% | 79% | 73% | 67% | 71% | 70% | 81% | 75% | 60% | 68% | 83% | 72% | 80% | |
| 92.6% | 95% | 96% | 88% | 94% | 82% | 92% | 93% | 91% | 92% | 94% | 97% | 94% | 93% | 98% | 94% | 96% | 98% | 94% | 91% | 85% | 87% |