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 GD2 (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 | 3rd 85.7% | 3rd 85.7% | 11th 83.7% | 12th 83.0% | 13th 81.7% | 19th 79.3% | 15th 81.0% | 5th 85.0% | 14th 81.3% | 18th 79.7% | 8th 84.3% | 2nd 86.7% | 8th 84.3% | 6th 84.3% | 15th 81.0% | 15th 81.0% | 1st 87.7% | 20th 74.7% | 6th 84.3% | 21st 73.3% | 8th 84.3% | |
| 90.0% | 98% | 87% | 92% | 92% | 98% | 80% | 92% | 91% | 94% | 91% | 85% | 94% | 94% | 92% | 93% | 88% | 100% | 87% | 88% | 67% | 87% | |
| 75.2% | 80% | 81% | 83% | 78% | 72% | 77% | 72% | 68% | 70% | 72% | 80% | 80% | 71% | 70% | 79% | 76% | 73% | 65% | 74% | 76% | 82% | |
| 82.2% | 79% | 89% | 76% | 79% | 75% | 81% | 79% | 96% | 80% | 76% | 88% | 86% | 88% | 91% | 71% | 79% | 90% | 72% | 91% | 77% | 84% |