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 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 | 16th 80.0% | 5th 84.3% | 18th 79.3% | 7th 83.0% | 21st 76.0% | 11th 81.3% | 14th 80.5% | 20th 77.0% | 18th 79.3% | 17th 79.8% | 1st 86.5% | 11th 81.3% | 6th 83.3% | 13th 81.2% | 15th 80.3% | 1st 86.5% | 4th 85.5% | 9th 82.5% | 8th 82.5% | 10th 81.5% | 3rd 86.3% | |
| 73.6% | 76% | 72% | 65% | 69% | 74% | 67% | 70% | 77% | 75% | 68% | 79% | 74% | 79% | 85% | 60% | 74% | 75% | 77% | 79% | 72% | 78% | |
| 85.3% | 80% | 91% | 76% | 89% | 72% | 91% | 89% | 73% | 75% | 83% | 93% | 89% | 90% | 84% | 84% | 89% | 90% | 81% | 85% | 90% | 97% | |
| 75.2% | 74% | 79% | 79% | 81% | 76% | 75% | 70% | 62% | 72% | 76% | 77% | 67% | 71% | 70% | 82% | 84% | 79% | 80% | 76% | 71% | 79% | |
| 93.0% | 90% | 95% | 97% | 93% | 82% | 92% | 93% | 96% | 95% | 92% | 97% | 95% | 93% | 86% | 95% | 99% | 98% | 92% | 90% | 93% | 91% |