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 Indonesia. 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 | 4th 83.7% | 2nd 84.8% | 9th 82.8% | 1st 86.5% | 20th 71.5% | 17th 76.3% | 11th 82.0% | 19th 75.3% | 18th 75.8% | 15th 80.3% | 8th 83.0% | 5th 83.5% | 10th 82.5% | 21st 69.5% | 16th 80.0% | 6th 83.3% | 13th 81.0% | 14th 80.8% | 6th 83.3% | 12th 81.3% | 3rd 84.0% | |
| 77.8% | 80% | 91% | 81% | 81% | 75% | 61% | 75% | 66% | 81% | 77% | 68% | 84% | 85% | 50% | 84% | 87% | 83% | 83% | 90% | 74% | 77% | |
| 87.5% | 89% | 89% | 84% | 87% | 74% | 83% | 87% | 91% | 91% | 85% | 98% | 92% | 85% | 91% | 87% | 91% | 82% | 82% | 87% | 84% | 98% | |
| 85.0% | 92% | 90% | 89% | 96% | 85% | 86% | 94% | 74% | 70% | 85% | 92% | 92% | 85% | 67% | 79% | 85% | 83% | 79% | 85% | 91% | ||
| 71.9% | 74% | 69% | 77% | 82% | 52% | 75% | 72% | 70% | 61% | 74% | 74% | 66% | 75% | 70% | 70% | 70% | 76% | 79% | 71% | 76% | 77% |