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 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 | 16th 77.7% | 1st 85.0% | 13th 79.3% | 8th 81.3% | 1st 85.0% | 18th 77.3% | 4th 82.3% | 10th 81.0% | 8th 81.3% | 15th 79.0% | 12th 80.0% | 3rd 83.3% | 16th 77.7% | 5th 82.0% | 19th 76.7% | 13th 79.3% | 6th 81.7% | 20th 76.3% | 6th 81.7% | 21st 74.7% | 11th 80.7% | |
| 91.2% | 82% | 88% | 87% | 88% | 95% | 87% | 92% | 98% | 95% | 96% | 91% | 92% | 92% | 95% | 90% | 90% | 93% | 91% | 92% | 91% | 90% | |
| 69.3% | 70% | 81% | 74% | 79% | 75% | 67% | 71% | 61% | 66% | 67% | 63% | 71% | 57% | 64% | 76% | 82% | 71% | 61% | 70% | 61% | 69% | |
| 80.0% | 81% | 86% | 77% | 77% | 85% | 78% | 84% | 84% | 83% | 74% | 86% | 87% | 84% | 87% | 64% | 66% | 81% | 77% | 83% | 72% | 83% |