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 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 | 8th 83.5% | 2nd 88.8% | 21st 76.8% | 15th 80.3% | 12th 81.5% | 18th 79.5% | 17th 79.8% | 20th 77.3% | 19th 79.3% | 14th 81.0% | 1st 89.5% | 11th 81.8% | 7th 83.8% | 5th 85.2% | 12th 81.5% | 8th 83.5% | 10th 83.3% | 16th 80.0% | 3rd 86.0% | 6th 84.0% | 4th 86.0% | |
| 80.7% | 82% | 86% | 71% | 72% | 80% | 71% | 76% | 81% | 78% | 71% | 96% | 85% | 86% | 96% | 65% | 79% | 90% | 72% | 89% | 85% | 84% | |
| 89.1% | 83% | 98% | 76% | 86% | 78% | 93% | 93% | 81% | 80% | 87% | 99% | 92% | 93% | 90% | 93% | 92% | 94% | 87% | 93% | 86% | 98% | |
| 67.3% | 75% | 74% | 67% | 67% | 77% | 63% | 67% | 58% | 64% | 71% | 67% | 62% | 60% | 65% | 75% | 72% | 58% | 69% | 67% | 67% | 69% | |
| 92.7% | 94% | 97% | 93% | 96% | 91% | 91% | 83% | 89% | 95% | 95% | 96% | 88% | 96% | 90% | 93% | 91% | 91% | 92% | 95% | 98% | 93% |