Compare AI models

Decision facts

• Gemma 4 31B is #29; GPT-5.5 is #13 on the same current language board.
• Index scores are 73.8 for Gemma 4 31B and 82.5 for GPT-5.5. 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 $0.34 for Gemma 4 31B and $30.00 for GPT-5.5. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $0.35 for Gemma 4 31B versus $25.00 for GPT-5.5. Gemma 4 31B costs 98.6% 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 262,144 tokens for Gemma 4 31B and 1,050,000 for GPT-5.5.
• Weight access differs: Gemma 4 31B is open; GPT-5.5 is none.
• ModelCap currently lists 11 providers for Gemma 4 31B and 3 for GPT-5.5.

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