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 46-55. 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 | 11th 76.5% | 1st 83.3% | 11th 76.5% | 15th 74.3% | 2nd 82.3% | 14th 75.3% | 9th 76.8% | 21st 71.5% | 15th 74.3% | 20th 71.8% | 5th 79.8% | 3rd 82.0% | 8th 79.3% | 9th 76.8% | 13th 76.3% | 4th 81.5% | 18th 73.5% | 6th 79.5% | 6th 79.5% | 17th 74.0% | 19th 72.3% | |
| 73.5% | 72% | 78% | 68% | 64% | 76% | 65% | 77% | 73% | 73% | 68% | 82% | 85% | 84% | 78% | 68% | 74% | 67% | 75% | 73% | 70% | 74% | |
| 72.8% | 69% | 76% | 74% | 70% | 80% | 75% | 70% | 64% | 69% | 67% | 82% | 81% | 75% | 73% | 69% | 70% | 75% | 78% | 75% | 70% | 67% | |
| 71.3% | 72% | 89% | 74% | 75% | 85% | 69% | 72% | 60% | 67% | 69% | 62% | 71% | 64% | 64% | 80% | 84% | 61% | 70% | 74% | 66% | 69% | |
| 90.3% | 93% | 90% | 90% | 88% | 88% | 92% | 88% | 89% | 88% | 83% | 93% | 91% | 94% | 92% | 88% | 98% | 91% | 95% | 96% | 90% | 79% |