GoKawiilMercury 2.5 benchmarked at 770 tokens per second, scores low on intelligence index
Mercury 2.5, a text-only large language model with a 260k token context window, has been benchmarked at 770 tokens per second on Artificial Analysis's testing. It scored 12 on the Intelligence Index, below the median of 13, while using fewer tokens (35M vs a median 85M) to complete the evaluation. Pricing sits at $0.25 per 1M input tokens and $0.75 per 1M output tokens, close to category medians.
GoKawiil's interpretation of the reporting above, not reported fact.
The benchmark suggests Mercury 2.5 trades intelligence for speed and concision, which could appeal to developers building latency-sensitive applications where raw reasoning depth matters less. Its pricing near the market median indicates it is not being positioned as a budget option but as a speed-focused alternative among similarly priced models.
- Mercury 2.5 runs at 770 tokens per second, well above typical model speeds
- It scores below the median on the Artificial Analysis Intelligence Index
- Pricing is roughly in line with comparable models at $0.25/$0.75 per 1M tokens
Source: artificialanalysis.ai, 2026-09-23
Published there as: “Mercury 2.5 LLM hits 770 tokens per second”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.