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 26-35. 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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 14th 79.7% | 4th 85.0% | 17th 79.0% | 13th 80.0% | 18th 78.7% | 12th 80.3% | 6th 84.0% | 21st 78.0% | 3rd 85.7% | 9th 81.7% | 8th 82.7% | 7th 83.3% | 18th 78.7% | 20th 78.3% | 9th 81.7% | 1st 86.0% | 5th 84.7% | 15th 79.7% | 1st 86.0% | 15th 79.7% | 11th 81.0% | |
| 92.4% | 88% | 96% | 87% | 90% | 84% | 89% | 95% | 87% | 96% | 92% | 96% | 98% | 91% | 90% | 94% | 98% | 97% | 90% | 98% | 92% | 92% | |
| 73.1% | 76% | 80% | 76% | 76% | 73% | 78% | 73% | 63% | 70% | 73% | 73% | 72% | 63% | 61% | 73% | 80% | 76% | 73% | 76% | 77% | 73% | |
| 79.3% | 75% | 79% | 74% | 74% | 79% | 74% | 84% | 84% | 91% | 80% | 79% | 80% | 82% | 84% | 78% | 80% | 81% | 76% | 84% | 70% | 78% |