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 26-35. 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 | 8th 84.7% | 3rd 87.3% | 17th 81.5% | 14th 82.3% | 19th 80.5% | 13th 83.0% | 12th 83.5% | 21st 76.3% | 10th 84.5% | 9th 84.5% | 6th 86.0% | 16th 81.8% | 4th 86.8% | 15th 82.2% | 5th 86.0% | 11th 84.3% | 18th 81.2% | 20th 79.0% | 1st 88.3% | 7th 85.5% | 2nd 87.8% | |
| 77.7% | 80% | 74% | 71% | 72% | 72% | 71% | 75% | 76% | 85% | 80% | 81% | 85% | 83% | 84% | 80% | 78% | 74% | 72% | 83% | 77% | 79% | |
| 86.2% | 87% | 87% | 78% | 90% | 85% | 88% | 89% | 74% | 78% | 86% | 88% | 85% | 92% | 85% | 88% | 86% | 85% | 91% | 88% | 87% | 94% | |
| 78.5% | 76% | 91% | 79% | 81% | 79% | 81% | 76% | 69% | 78% | 83% | 79% | 76% | 73% | 74% | 79% | 77% | 76% | 60% | 91% | 84% | 87% | |
| 92.1% | 96% | 97% | 98% | 86% | 86% | 92% | 94% | 86% | 97% | 89% | 96% | 81% | 99% | 86% | 97% | 96% | 90% | 93% | 91% | 94% | 91% |