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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 17th 80.8% | 3rd 84.5% | 20th 77.8% | 14th 81.3% | 18th 80.0% | 13th 81.5% | 16th 81.0% | 21st 77.5% | 19th 78.8% | 11th 82.5% | 1st 86.0% | 7th 84.0% | 9th 83.0% | 10th 82.8% | 3rd 84.5% | 5th 84.3% | 12th 82.3% | 8th 84.0% | 5th 84.3% | 14th 81.3% | 2nd 85.8% | |
| 74.9% | 76% | 72% | 65% | 69% | 71% | 67% | 70% | 77% | 73% | 74% | 79% | 84% | 81% | 84% | 79% | 74% | 75% | 77% | 75% | 72% | 78% | |
| 86.2% | 80% | 91% | 80% | 89% | 85% | 92% | 91% | 73% | 75% | 86% | 94% | 85% | 91% | 86% | 84% | 90% | 90% | 90% | 85% | 82% | 92% | |
| 75.3% | 74% | 79% | 79% | 73% | 82% | 75% | 70% | 64% | 72% | 76% | 73% | 72% | 71% | 74% | 82% | 78% | 71% | 75% | 79% | 80% | 82% | |
| 92.7% | 93% | 96% | 87% | 94% | 82% | 92% | 93% | 96% | 95% | 94% | 98% | 95% | 89% | 87% | 93% | 95% | 93% | 94% | 98% | 91% | 91% |