jamba-mini-1.7 vs kimi-k2-0905-preview

Capability for the money

Not the same tier: kimi-k2-0905-preview leads jamba-mini-1.7 by 54.9 points on coding (LiveCodeBench), for 4.3× the price.

1. Following instructions

   extraction, classification, sticking to a format

   IFBench
   jamba-mini-1.731.4%

   kimi-k2-0905-preview41.7%

   kimi-k2-0905-preview +10.3

2. Coding

   writing and fixing code

   LiveCodeBench
   jamba-mini-1.76.1%

   kimi-k2-0905-preview61.0%

   kimi-k2-0905-preview +54.9

3. Tool use

   multi-step agent work against real tools

   τ²-bench
   jamba-mini-1.712.6%

   kimi-k2-0905-preview73.4%

   kimi-k2-0905-preview +60.8

4. Hard reasoning

   graduate-level science and multi-step analysis

   GPQA Diamond
   jamba-mini-1.732.2%

   kimi-k2-0905-preview76.7%

   kimi-k2-0905-preview +44.5

Averaged over the benchmarks both models sat, jamba-mini-1.7 returns 82.3 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.