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 | 1st 85.0% | 8th 73.5% | 12th 71.5% | 3rd 76.8% | 16th 67.5% | 9th 73.3% | 12th 71.5% | 6th 74.3% | 19th 65.3% | 20th 63.8% | 11th 72.0% | 10th 72.2% | 17th 66.8% | 4th 75.8% | 2nd 79.3% | 5th 74.5% | 18th 66.3% | 14th 71.2% | 15th 69.3% | 21st 58.8% | 7th 73.8% | |
| 67.6% | 100% | 56% | 57% | 67% | 77% | 60% | 59% | 65% | 51% | 63% | 60% | 61% | 63% | 71% | 100% | 71% | 55% | 67% | 54% | 63% | 100% | |
| 85.5% | 95% | 94% | 82% | 81% | 71% | 87% | 91% | 89% | 88% | 80% | 91% | 88% | 88% | 93% | 83% | 87% | 88% | 82% | 88% | 71% | 78% | |
| 56.5% | 62% | 61% | 67% | 76% | 63% | 59% | 53% | 60% | 54% | 51% | 50% | 52% | 49% | 52% | 66% | 70% | 49% | 42% | 54% | 39% | 58% | |
| 76.5% | 83% | 83% | 80% | 83% | 59% | 87% | 83% | 83% | 68% | 61% | 87% | 88% | 67% | 87% | 68% | 70% | 73% | 94% | 81% | 62% | 59% |