Compare AI models

Decision facts

• Gemma 3 12B is #133; gpt-oss-20b is #135 on the same current language board.
• Index scores are 30.0 for Gemma 3 12B and 27.9 for gpt-oss-20b. 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 $0.15 for Gemma 3 12B and $0.13 for gpt-oss-20b. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $0.17 for Gemma 3 12B versus $0.13 for gpt-oss-20b. gpt-oss-20b costs 28.6% 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 12B and 131,072 for gpt-oss-20b.
• Weight access differs: Gemma 3 12B is gated; gpt-oss-20b is open.
• ModelCap currently lists 1 providers for Gemma 3 12B and 12 for gpt-oss-20b.

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