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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 1st 92.0% | 10th 83.5% | 7th 84.0% | 5th 85.5% | 13th 83.0% | 9th 83.8% | 3rd 85.8% | 2nd 86.3% | 21st 75.8% | 20th 76.5% | 17th 81.8% | 18th 81.5% | 7th 84.0% | 11th 83.3% | 15th 82.7% | 19th 79.5% | 12th 83.0% | 6th 85.0% | 4th 85.8% | 13th 83.0% | 16th 82.0% | |
| 63.0% | 100% | 57% | 66% | 66% | 70% | 66% | 68% | 62% | 58% | 55% | 41% | 68% | 63% | 59% | 57% | 61% | 61% | 72% | 57% | 57% | 59% | |
| 88.3% | 81% | 95% | 87% | 94% | 83% | 89% | 92% | 97% | 74% | 72% | 91% | 78% | 92% | 92% | 92% | 91% | 90% | 90% | 92% | 92% | 90% | |
| 89.0% | 89% | 94% | 91% | 91% | 91% | 94% | 93% | 89% | 82% | 85% | 96% | 88% | 87% | 88% | 85% | 78% | 84% | 84% | 99% | 91% | 90% | |
| 92.6% | 98% | 88% | 92% | 91% | 88% | 86% | 90% | 97% | 89% | 94% | 99% | 92% | 94% | 94% | 97% | 88% | 97% | 94% | 95% | 92% | 89% |