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 | 10th 82.3% | 6th 83.5% | 21st 77.3% | 9th 83.0% | 17th 79.5% | 13th 81.3% | 15th 81.0% | 20th 77.5% | 18th 79.5% | 10th 82.3% | 1st 86.5% | 7th 83.3% | 14th 81.0% | 3rd 85.2% | 19th 78.3% | 16th 80.8% | 5th 83.8% | 4th 84.3% | 10th 82.3% | 7th 83.3% | 2nd 85.3% | |
| 74.6% | 78% | 72% | 67% | 69% | 80% | 67% | 70% | 80% | 80% | 72% | 81% | 79% | 75% | 84% | 70% | 65% | 75% | 73% | 75% | 77% | 78% | |
| 86.0% | 77% | 87% | 76% | 89% | 82% | 91% | 91% | 73% | 71% | 88% | 95% | 89% | 90% | 85% | 83% | 90% | 91% | 91% | 85% | 90% | 92% | |
| 74.2% | 77% | 79% | 79% | 81% | 68% | 75% | 70% | 61% | 72% | 75% | 74% | 71% | 68% | 74% | 68% | 78% | 71% | 79% | 79% | 79% | 81% | |
| 92.9% | 97% | 96% | 87% | 93% | 88% | 92% | 93% | 96% | 95% | 94% | 96% | 94% | 91% | 98% | 92% | 90% | 98% | 94% | 90% | 87% | 90% |