Compare AI models

Decision facts

• Gemma 3 4B is #146; Granite 4.2 8B is #147 on the same current language board.
• Index scores are 19.3 for Gemma 3 4B and 18.7 for Granite 4.2 8B. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.
• Both positions use Measured evidence.
• Listed output price per 1M tokens is $0.10 for Gemma 3 4B and $0.25 for Granite 4.2 8B. 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 Gemma 3 4B versus $0.24 for Granite 4.2 8B. Gemma 3 4B costs 38.8% 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 131,072 tokens for Gemma 3 4B and 131,072 for Granite 4.2 8B.
• Weight access differs: Gemma 3 4B is gated; Granite 4.2 8B is open.
• ModelCap currently lists 1 providers for Gemma 3 4B and 2 for Granite 4.2 8B.

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