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 Kazakhstan. 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 | 15th 72.7% | 16th 72.3% | 6th 78.0% | 2nd 80.7% | 3rd 79.3% | 21st 66.7% | 1st 81.0% | 14th 73.0% | 9th 76.0% | 11th 74.7% | 13th 74.3% | 7th 77.3% | 19th 71.3% | 16th 72.3% | 8th 76.3% | 11th 74.7% | 20th 67.7% | 16th 72.3% | 5th 78.7% | 4th 79.0% | 10th 75.7% | |
| 73.8% | 61% | 66% | 76% | 76% | 78% | 76% | 90% | 76% | 74% | 76% | 71% | 76% | 72% | 78% | 69% | 70% | 67% | 67% | 76% | 78% | 77% | |
| 59.9% | 65% | 62% | 66% | 71% | 71% | 41% | 62% | 48% | 61% | 58% | 61% | 62% | 47% | 54% | 69% | 66% | 49% | 53% | 66% | 63% | 62% | |
| 91.2% | 92% | 89% | 92% | 95% | 89% | 83% | 91% | 95% | 93% | 90% | 91% | 94% | 95% | 85% | 91% | 88% | 87% | 97% | 94% | 96% | 88% |