Moonshot vs Perplexity · synced 2026-08-11

kimi-k2-0905-preview vs llama-3.1-8b-instruct

llama-3.1-8b-instruct is 3.0× cheaper on input than kimi-k2-0905-preview.

kimi-k2-0905-preview llama-3.1-8b-instruct
Input / 1M $0.60 $0.20
Cached input / 1M $0.15
Output / 1M $2.50 $0.20
Context window 262K 131K
Max output 262K 131K
Provider Moonshot Perplexity
Vision No No
Tool calling Yes No
Token count estimated estimated

Capability for the money

Independent measurement · Artificial Analysis · read 2026-08-11

Not the same tier: kimi-k2-0905-preview leads llama-3.1-8b-instruct by 50.8 points on hard reasoning (GPQA Diamond), for 5.4× the price.

  1. Following instructions

    extraction, classification, sticking to a format

    IFBench
    kimi-k2-0905-preview41.7%
    llama-3.1-8b-instruct28.6%

    kimi-k2-0905-preview +13.1

  2. Coding

    writing and fixing code

    LiveCodeBench
    kimi-k2-0905-preview61.0%
    llama-3.1-8b-instruct11.6%

    kimi-k2-0905-preview +49.4

  3. Tool use

    multi-step agent work against real tools

    τ²-bench
    kimi-k2-0905-preview73.4%
    llama-3.1-8b-instruct16.4%

    kimi-k2-0905-preview +57.0

  4. Hard reasoning

    graduate-level science and multi-step analysis

    GPQA Diamond
    kimi-k2-0905-preview76.7%
    llama-3.1-8b-instruct25.9%

    kimi-k2-0905-preview +50.8

Averaged over the benchmarks both models sat, llama-3.1-8b-instruct returns 103.1 points of pass rate per dollar of blended price against 58.8 — the ratio that decides whether the dearer model earns its rate.

Each figure is a pass rate: the share of that test set the model answered correctly, measured by a third party rather than self-reported by the lab. Rows are different tests of different difficulty, so compare a model against the other model, not one row against the next. And a benchmark is not your workload — it narrows the shortlist, it does not pick for you.

Which to pick

List price is not production cost. Output length, cache hit rate, retries and task quality move the real number more than the headline rate does — price your own prompt on the token ledger before deciding.

Related comparisons