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 excited than concerned. 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 89.0% | 3rd 84.3% | 7th 78.0% | 17th 72.3% | 6th 80.5% | 5th 83.3% | 18th 72.0% | 21st 66.3% | 19th 71.8% | 15th 72.7% | 11th 74.8% | 16th 72.5% | 14th 73.5% | 13th 74.3% | 2nd 87.3% | 9th 77.0% | 12th 74.5% | 10th 76.0% | 8th 77.8% | 20th 69.5% | 3rd 84.3% | |
| 66.7% | 100% | 66% | 61% | 66% | 72% | 73% | 61% | 54% | 55% | 58% | 55% | 52% | 59% | 53% | 100% | 66% | 57% | 63% | 66% | 63% | 100% | |
| 75.9% | 75% | 89% | 75% | 62% | 88% | 83% | 74% | 66% | 67% | 74% | 78% | 75% | 79% | 73% | 79% | 73% | 82% | 77% | 78% | 66% | 80% | |
| 77.9% | 87% | 92% | 83% | 80% | 81% | 88% | 72% | 61% | 77% | 74% | 74% | 72% | 72% | 78% | 81% | 78% | 74% | 77% | 83% | 74% | 78% | |
| 86.5% | 94% | 90% | 93% | 81% | 81% | 89% | 81% | 84% | 88% | 85% | 92% | 91% | 84% | 93% | 89% | 91% | 85% | 87% | 84% | 75% | 79% |