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 | 4th 84.8% | 8th 78.8% | 11th 78.0% | 5th 83.5% | 21st 67.0% | 9th 78.5% | 15th 74.8% | 13th 76.5% | 7th 80.0% | 6th 80.5% | 14th 75.3% | 18th 72.3% | 16th 73.3% | 16th 73.3% | 2nd 89.0% | 1st 90.8% | 20th 70.5% | 12th 76.8% | 10th 78.3% | 18th 72.3% | 3rd 88.3% | |
| 66.6% | 100% | 54% | 57% | 69% | 76% | 51% | 63% | 47% | 46% | 61% | 57% | 100% | 57% | 55% | 100% | 100% | 51% | 48% | 48% | 59% | 100% | |
| 88.1% | 91% | 83% | 83% | 99% | 73% | 92% | 91% | 95% | 97% | 96% | 88% | 67% | 80% | 93% | 92% | 93% | 87% | 93% | 93% | 76% | 89% | |
| 68.3% | 66% | 81% | 75% | 76% | 58% | 77% | 56% | 72% | 77% | 73% | 63% | 35% | 62% | 54% | 79% | 78% | 64% | 79% | 76% | 63% | 71% | |
| 89.7% | 82% | 97% | 97% | 90% | 61% | 94% | 89% | 92% | 100% | 92% | 93% | 87% | 94% | 91% | 85% | 92% | 80% | 87% | 96% | 91% | 93% |