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 36-45. 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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 4th 84.0% | 5th 83.3% | 10th 80.7% | 5th 83.3% | 18th 79.3% | 21st 77.3% | 10th 80.7% | 9th 81.0% | 12th 80.3% | 16th 79.7% | 12th 80.3% | 7th 82.0% | 20th 78.3% | 1st 86.0% | 14th 80.0% | 16th 79.7% | 3rd 85.0% | 8th 81.3% | 1st 86.0% | 14th 80.0% | 18th 79.3% | |
| 90.1% | 96% | 89% | 97% | 97% | 84% | 82% | 91% | 94% | 90% | 92% | 89% | 84% | 89% | 98% | 94% | 94% | 94% | 82% | 91% | 83% | 83% | |
| 72.8% | 74% | 81% | 76% | 76% | 73% | 73% | 67% | 63% | 68% | 73% | 73% | 73% | 60% | 67% | 79% | 75% | 74% | 73% | 75% | 73% | 83% | |
| 81.0% | 82% | 80% | 69% | 77% | 81% | 77% | 84% | 86% | 83% | 74% | 79% | 89% | 86% | 93% | 67% | 70% | 87% | 89% | 92% | 84% | 72% |