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 18-25. 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 | 10th 84.5% | 1st 87.3% | 10th 84.5% | 2nd 86.5% | 16th 82.5% | 17th 82.5% | 13th 83.5% | 21st 77.0% | 12th 83.8% | 5th 85.5% | 8th 84.8% | 20th 81.0% | 4th 86.3% | 19th 81.5% | 6th 85.0% | 8th 84.8% | 18th 82.0% | 6th 85.0% | 2nd 86.5% | 15th 83.0% | 14th 83.3% | |
| 81.2% | 79% | 79% | 77% | 81% | 79% | 73% | 76% | 82% | 88% | 84% | 82% | 90% | 84% | 87% | 89% | 80% | 81% | 78% | 82% | 73% | 81% | |
| 84.7% | 91% | 86% | 90% | 90% | 76% | 83% | 92% | 75% | 78% | 84% | 88% | 81% | 93% | 81% | 81% | 87% | 83% | 90% | 86% | 82% | 81% | |
| 79.4% | 77% | 90% | 78% | 80% | 81% | 82% | 76% | 72% | 79% | 83% | 76% | 73% | 75% | 75% | 79% | 81% | 77% | 79% | 87% | 83% | 84% | |
| 90.1% | 91% | 94% | 93% | 95% | 94% | 92% | 90% | 79% | 90% | 91% | 93% | 80% | 93% | 83% | 91% | 91% | 87% | 93% | 91% | 94% | 87% |