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 More concerned than excited. 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 | 3rd 87.0% | 12th 77.3% | 11th 77.3% | 6th 83.5% | 20th 65.0% | 14th 77.0% | 5th 83.5% | 9th 77.8% | 7th 81.8% | 8th 80.5% | 16th 73.5% | 18th 72.0% | 19th 71.5% | 17th 73.0% | 1st 91.5% | 2nd 89.0% | 10th 77.5% | 15th 74.0% | 13th 77.0% | 21st 62.7% | 4th 86.0% | |
| 68.9% | 100% | 54% | 57% | 69% | 59% | 51% | 100% | 56% | 53% | 64% | 57% | 100% | 56% | 54% | 100% | 100% | 61% | 48% | 49% | 59% | 100% | |
| 86.5% | 94% | 82% | 91% | 99% | 81% | 87% | 90% | 94% | 97% | 98% | 88% | 67% | 80% | 92% | 93% | 87% | 84% | 92% | 91% | 42% | ||
| 68.5% | 71% | 76% | 76% | 76% | 63% | 76% | 55% | 69% | 77% | 70% | 62% | 35% | 63% | 53% | 79% | 78% | 76% | 69% | 76% | 69% | 69% | |
| 88.2% | 83% | 97% | 85% | 90% | 57% | 94% | 89% | 92% | 100% | 90% | 87% | 86% | 87% | 93% | 94% | 91% | 89% | 87% | 92% | 81% | 89% |