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 Australia. 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 | 9th 77.0% | 1st 81.7% | 12th 76.8% | 14th 76.5% | 7th 78.3% | 18th 71.5% | 8th 77.5% | 2nd 80.5% | 9th 77.0% | 15th 76.3% | 16th 75.3% | 6th 78.5% | 4th 79.5% | 13th 76.5% | 5th 78.5% | 9th 77.0% | 18th 71.5% | 17th 72.8% | 21st 56.8% | 3rd 80.3% | 20th 70.8% | |
| 78.9% | 81% | 82% | 74% | 71% | 74% | 72% | 83% | 78% | 81% | 81% | 80% | 85% | 82% | 85% | 82% | 80% | 74% | 73% | 82% | 82% | 75% | |
| 80.7% | 80% | 100% | 90% | 86% | 86% | 81% | 82% | 100% | 81% | 76% | 81% | 86% | 87% | 75% | 86% | 81% | 82% | 82% | 0% | 90% | 82% | |
| 65.2% | 65% | 71% | 65% | 75% | 71% | 61% | 69% | 66% | 65% | 61% | 75% | 65% | 71% | 59% | 65% | 66% | 56% | 62% | 58% | 71% | 52% | |
| 78.1% | 82% | 74% | 78% | 74% | 82% | 72% | 76% | 78% | 81% | 87% | 65% | 78% | 78% | 87% | 81% | 81% | 74% | 74% | 87% | 78% | 74% |