kimi-k2-0905-preview vs llama-3.1-70b-instruct

Capability for the money

Both are priced within 15% of each other, so capability decides it: kimi-k2-0905-preview leads by 58.2 points on tool use (τ²-bench).

1. Following instructions

   extraction, classification, sticking to a format

   IFBench
   kimi-k2-0905-preview41.7%

   llama-3.1-70b-instruct34.4%

   kimi-k2-0905-preview +7.3

2. Coding

   writing and fixing code

   LiveCodeBench
   kimi-k2-0905-preview61.0%

   llama-3.1-70b-instruct23.2%

   kimi-k2-0905-preview +37.8

3. Tool use

   multi-step agent work against real tools

   τ²-bench
   kimi-k2-0905-preview73.4%

   llama-3.1-70b-instruct15.2%

   kimi-k2-0905-preview +58.2

4. Hard reasoning

   graduate-level science and multi-step analysis

   GPQA Diamond
   kimi-k2-0905-preview76.7%

   llama-3.1-70b-instruct40.9%

   kimi-k2-0905-preview +35.8

Averaged over the benchmarks both models sat, kimi-k2-0905-preview returns 58.8 points of pass rate per dollar of blended price against 28.4 — 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.