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 92.3% | 10th 84.0% | 7th 85.5% | 4th 87.8% | 3rd 89.5% | 11th 83.5% | 5th 86.5% | 20th 76.8% | 19th 78.8% | 16th 81.3% | 12th 83.0% | 21st 73.8% | 18th 80.5% | 17th 80.5% | 1st 93.3% | 5th 86.5% | 14th 82.0% | 15th 82.0% | 9th 84.3% | 8th 84.5% | 13th 82.3% | |
| 67.4% | 100% | 66% | 66% | 75% | 76% | 66% | 62% | 59% | 55% | 61% | 63% | 67% | 58% | 61% | 100% | 82% | 61% | 63% | 61% | 59% | 55% | |
| 87.1% | 87% | 87% | 94% | 85% | 88% | 89% | 97% | 75% | 76% | 74% | 92% | 87% | 90% | 91% | 90% | 78% | 90% | 87% | 92% | 90% | 91% | |
| 86.1% | 86% | 91% | 91% | 92% | 96% | 94% | 88% | 82% | 85% | 93% | 85% | 57% | 77% | 77% | 91% | 89% | 84% | 84% | 92% | 91% | 84% | |
| 94.2% | 96% | 92% | 91% | 99% | 98% | 85% | 99% | 91% | 99% | 97% | 92% | 84% | 97% | 93% | 92% | 97% | 93% | 94% | 92% | 98% | 99% |