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 | 2nd 91.5% | 10th 84.3% | 5th 87.0% | 7th 85.0% | 6th 86.0% | 12th 83.8% | 4th 87.3% | 21st 76.5% | 20th 78.8% | 15th 83.3% | 8th 84.8% | 13th 83.5% | 13th 83.5% | 17th 80.5% | 3rd 90.3% | 18th 80.3% | 16th 82.8% | 18th 80.3% | 10th 84.3% | 9th 84.5% | 1st 92.8% | |
| 68.5% | 100% | 66% | 72% | 73% | 76% | 66% | 62% | 57% | 55% | 61% | 63% | 72% | 59% | 61% | 100% | 61% | 60% | 57% | 61% | 57% | 100% | |
| 87.0% | 83% | 88% | 94% | 79% | 81% | 89% | 97% | 75% | 76% | 85% | 91% | 90% | 92% | 91% | 80% | 82% | 91% | 92% | 92% | 87% | 91% | |
| 88.2% | 86% | 91% | 91% | 89% | 92% | 95% | 93% | 82% | 85% | 92% | 91% | 84% | 87% | 77% | 89% | 83% | 87% | 84% | 92% | 95% | 88% | |
| 93.5% | 97% | 92% | 91% | 99% | 95% | 85% | 97% | 92% | 99% | 95% | 94% | 88% | 96% | 93% | 92% | 95% | 93% | 88% | 92% | 99% | 92% |