Compare AI models

Decision facts

• GLM 4.6V is #109; GLM 5V Turbo is #45 on the same current language board.
• Index scores are 48.5 for GLM 4.6V and 68.8 for GLM 5V Turbo. 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 $0.90 for GLM 4.6V and $4.00 for GLM 5V Turbo. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $1.05 for GLM 4.6V versus $4.40 for GLM 5V Turbo. GLM 4.6V costs 76.1% 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 GLM 4.6V and 202,752 for GLM 5V Turbo.
• Weight access differs: GLM 4.6V is open; GLM 5V Turbo is none.
• ModelCap currently lists 2 providers for GLM 4.6V and 1 for GLM 5V Turbo.

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