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 46-55. 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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 14th 76.5% | 4th 81.5% | 20th 74.0% | 16th 75.5% | 11th 77.8% | 6th 81.2% | 9th 79.0% | 21st 73.8% | 13th 76.7% | 12th 76.8% | 1st 82.5% | 19th 74.8% | 3rd 81.7% | 2nd 82.0% | 17th 75.0% | 10th 78.3% | 7th 80.3% | 8th 79.8% | 5th 81.3% | 15th 75.5% | 17th 75.0% | |
| 76.2% | 75% | 78% | 68% | 65% | 78% | 73% | 77% | 74% | 71% | 85% | 83% | 87% | 87% | 63% | 71% | 80% | 80% | 80% | 82% | 66% | ||
| 75.9% | 73% | 82% | 69% | 73% | 70% | 82% | 81% | 70% | 70% | 78% | 83% | 75% | 78% | 79% | 78% | 75% | 76% | 77% | 75% | 73% | 76% | |
| 74.6% | 76% | 80% | 75% | 80% | 75% | 80% | 73% | 67% | 73% | 77% | 75% | 52% | 78% | 72% | 75% | 81% | 75% | 79% | 82% | 58% | 83% | |
| 85.5% | 82% | 86% | 84% | 84% | 88% | 90% | 85% | 84% | 87% | 81% | 87% | 89% | 84% | 90% | 84% | 86% | 90% | 83% | 88% | 89% | 75% |