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 GD2 (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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 90.7% | 9th 78.3% | 7th 78.7% | 6th 79.0% | 5th 81.7% | 11th 77.7% | 15th 75.3% | 20th 73.3% | 16th 74.7% | 12th 77.3% | 17th 74.7% | 21st 70.3% | 18th 74.3% | 18th 74.3% | 4th 84.7% | 1st 94.0% | 14th 77.0% | 10th 78.3% | 7th 78.7% | 12th 77.3% | 2nd 92.7% | |
| 89.9% | 98% | 88% | 86% | 93% | 99% | 81% | 94% | 92% | 87% | 95% | 86% | 85% | 92% | 85% | 95% | 97% | 89% | 80% | 86% | 90% | 90% | |
| 79.6% | 74% | 81% | 84% | 78% | 71% | 86% | 75% | 75% | 81% | 76% | 75% | 71% | 70% | 75% | 90% | 85% | 82% | 83% | 89% | 83% | 88% | |
| 68.0% | 100% | 66% | 66% | 66% | 75% | 66% | 57% | 53% | 56% | 61% | 63% | 55% | 61% | 63% | 69% | 100% | 60% | 72% | 61% | 59% | 100% |