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 18-25. 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 | 13th 83.5% | 1st 88.5% | 11th 84.5% | 3rd 86.5% | 17th 82.3% | 16th 82.5% | 12th 84.2% | 21st 75.8% | 15th 83.0% | 3rd 86.5% | 6th 86.3% | 20th 76.5% | 8th 85.8% | 18th 82.0% | 7th 86.0% | 2nd 87.3% | 19th 81.3% | 13th 83.5% | 3rd 86.5% | 8th 85.8% | 10th 85.0% | |
| 81.4% | 81% | 87% | 77% | 81% | 80% | 73% | 80% | 84% | 85% | 86% | 85% | 90% | 83% | 87% | 84% | 82% | 78% | 72% | 81% | 73% | 81% | |
| 85.6% | 86% | 86% | 90% | 90% | 85% | 83% | 91% | 75% | 78% | 86% | 87% | 81% | 90% | 83% | 81% | 88% | 83% | 85% | 86% | 89% | 95% | |
| 79.1% | 76% | 90% | 78% | 80% | 81% | 82% | 76% | 65% | 79% | 83% | 81% | 57% | 79% | 75% | 84% | 86% | 76% | 84% | 91% | 87% | 72% | |
| 89.6% | 91% | 91% | 93% | 95% | 83% | 92% | 90% | 79% | 90% | 91% | 92% | 78% | 91% | 83% | 95% | 93% | 88% | 93% | 88% | 94% | 92% |