Compare AI models

Decision facts

• Mercury 2.5 is #117; Mistral Small 3.2 24B is #120 on the same current language board.
• Index scores are 37.1 for Mercury 2.5 and 35.6 for Mistral Small 3.2 24B. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.
• Evidence differs: Mercury 2.5 is Estimated; Mistral Small 3.2 24B is Measured.
• Listed output price per 1M tokens is $0.15 for Mercury 2.5 and $0.20 for Mistral Small 3.2 24B. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $0.15 for Mercury 2.5 versus $0.25 for Mistral Small 3.2 24B. Mercury 2.5 costs 38.0% less in this scenario. This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the selected endpoint before budgeting.
• Published context is 260,000 tokens for Mercury 2.5 and 131,072 for Mistral Small 3.2 24B.
• Weight access differs: Mercury 2.5 is none; Mistral Small 3.2 24B is open.
• ModelCap currently lists 1 providers for Mercury 2.5 and 2 for Mistral Small 3.2 24B.

These are separate published fields, not a synthetic winner. ModelCap does not collapse price, access, context, and capability evidence into a hidden recommendation score.