Compare AI models

Decision facts

• GPT-4o (2024-08-06) is #195; gpt-oss-20b is #223 on the same current language board.
• Index scores are 36.2 for GPT-4o (2024-08-06) and 31.9 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 $10.00 for GPT-4o (2024-08-06) 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-4o (2024-08-06) 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 128,000 tokens for GPT-4o (2024-08-06) and 131,072 for gpt-oss-20b.
• Weight access differs: GPT-4o (2024-08-06) is none; gpt-oss-20b is open.
• ModelCap currently lists 2 providers for GPT-4o (2024-08-06) and 10 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.