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 86.8% | 1st 88.8% | 10th 84.5% | 2nd 86.8% | 16th 81.8% | 15th 82.0% | 11th 84.5% | 20th 76.0% | 13th 83.8% | 6th 86.0% | 14th 83.0% | 21st 75.8% | 7th 85.3% | 17th 81.5% | 2nd 86.8% | 5th 86.5% | 19th 77.5% | 18th 79.3% | 7th 85.3% | 12th 84.0% | 9th 84.8% | |
| 80.7% | 81% | 87% | 77% | 81% | 76% | 73% | 80% | 83% | 88% | 84% | 77% | 88% | 85% | 88% | 83% | 77% | 81% | 73% | 79% | 78% | 75% | |
| 85.6% | 90% | 86% | 90% | 90% | 85% | 81% | 91% | 75% | 78% | 86% | 88% | 81% | 91% | 86% | 88% | 88% | 82% | 82% | 86% | 81% | 92% | |
| 78.2% | 81% | 90% | 78% | 80% | 83% | 82% | 76% | 66% | 79% | 83% | 74% | 59% | 73% | 74% | 86% | 87% | 61% | 70% | 87% | 89% | 85% | |
| 88.9% | 95% | 92% | 93% | 96% | 83% | 92% | 91% | 80% | 90% | 91% | 93% | 75% | 92% | 78% | 90% | 94% | 86% | 92% | 89% | 88% | 87% |