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 GD2 (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 | 18th 72.3% | 2nd 79.0% | 6th 76.7% | 19th 72.0% | 1st 81.7% | 21st 71.3% | 6th 76.7% | 17th 73.0% | 9th 75.7% | 13th 74.0% | 8th 76.3% | 3rd 78.7% | 15th 73.7% | 4th 77.7% | 12th 74.0% | 4th 77.7% | 11th 74.3% | 15th 73.7% | 10th 75.3% | 20th 71.7% | 13th 74.0% | |
| 91.4% | 85% | 86% | 98% | 83% | 97% | 80% | 94% | 96% | 98% | 94% | 94% | 91% | 94% | 98% | 93% | 89% | 93% | 88% | 92% | 88% | 88% | |
| 69.9% | 71% | 79% | 74% | 78% | 79% | 77% | 69% | 60% | 68% | 73% | 62% | 71% | 61% | 63% | 79% | 80% | 60% | 60% | 70% | 62% | 71% | |
| 64.4% | 61% | 72% | 58% | 55% | 69% | 57% | 67% | 63% | 61% | 55% | 73% | 74% | 66% | 72% | 50% | 64% | 70% | 73% | 64% | 65% | 63% |