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 | 2nd 80.5% | 1st 81.0% | 12th 75.0% | 7th 76.8% | 3rd 80.0% | 8th 75.5% | 14th 74.5% | 20th 71.0% | 19th 72.8% | 17th 73.5% | 8th 75.5% | 6th 77.3% | 18th 73.0% | 15th 74.3% | 5th 77.5% | 4th 79.3% | 16th 73.8% | 13th 74.5% | 8th 75.5% | 21st 68.7% | 11th 75.5% | |
| 78.0% | 78% | 79% | 77% | 77% | 76% | 77% | 79% | 80% | 79% | 82% | 76% | 82% | 79% | 82% | 78% | 80% | 78% | 76% | 75% | 70% | 79% | |
| 77.9% | 83% | 83% | 76% | 76% | 81% | 77% | 84% | 72% | 77% | 74% | 82% | 82% | 77% | 81% | 74% | 78% | 75% | 75% | 76% | 72% | 81% | |
| 66.6% | 72% | 74% | 75% | 77% | 81% | 60% | 59% | 51% | 57% | 61% | 63% | 70% | 57% | 57% | 77% | 77% | 61% | 61% | 72% | 70% | ||
| 79.3% | 89% | 88% | 72% | 77% | 82% | 88% | 76% | 81% | 78% | 77% | 81% | 75% | 79% | 77% | 81% | 82% | 81% | 86% | 79% | 64% | 72% |