Compare AI models

Decision facts

• GPT-5.6 Terra is #21; gpt-oss-20b is #162 on the same current language board.
• Index scores are 79.7 for GPT-5.6 Terra and 35.3 for gpt-oss-20b. Their published uncertainty intervals do not overlap, but the aggregate Index does not predict performance on every task; compare the relevant benchmark configurations before choosing.
• Both positions use Measured evidence.
• Listed output price per 1M tokens is $12.00 for GPT-5.6 Terra and $0.09 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 $10.00 for GPT-5.6 Terra versus $0.08 for gpt-oss-20b. gpt-oss-20b costs 99.2% 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 1,050,000 tokens for GPT-5.6 Terra and 131,072 for gpt-oss-20b.
• Weight access differs: GPT-5.6 Terra is none; gpt-oss-20b is open.
• ModelCap currently lists 3 providers for GPT-5.6 Terra and 11 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.