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 56-65. 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 | 5th 86.0% | 3rd 87.3% | 4th 86.3% | 7th 83.0% | 11th 82.7% | 20th 78.7% | 17th 81.0% | 13th 82.0% | 7th 83.0% | 18th 80.0% | 9th 83.0% | 1st 90.0% | 9th 83.0% | 14th 81.7% | 14th 81.7% | 21st 78.3% | 6th 84.7% | 19th 79.0% | 2nd 88.3% | 12th 82.3% | 16th 81.3% | |
| 90.3% | 98% | 92% | 92% | 92% | 90% | 80% | 92% | 82% | 100% | 90% | 85% | 98% | 90% | 78% | 91% | 83% | 100% | 87% | 98% | 91% | 87% | |
| 75.0% | 81% | 81% | 88% | 78% | 75% | 75% | 72% | 68% | 70% | 71% | 80% | 75% | 71% | 70% | 82% | 75% | 68% | 66% | 79% | 72% | 77% | |
| 83.8% | 79% | 89% | 79% | 79% | 83% | 81% | 79% | 96% | 79% | 79% | 84% | 97% | 88% | 97% | 72% | 77% | 86% | 84% | 88% | 84% | 80% |