llama-3.1-8b-instant vs ministral-8b-latest

Capability for the money

Not the same tier: ministral-8b-latest leads llama-3.1-8b-instant by 21.2 points on hard reasoning (GPQA Diamond), for 2.6× the price. They are level on following instructions (IFBench), so the premium only pays off on hard reasoning work.

1. Following instructions

   extraction, classification, sticking to a format

   IFBench
   llama-3.1-8b-instant28.6%

   ministral-8b-latest29.1%

   ministral-8b-latest +0.5

2. Coding

   writing and fixing code

   LiveCodeBench
   llama-3.1-8b-instant11.6%

   ministral-8b-latest30.3%

   ministral-8b-latest +18.7

3. Tool use

   multi-step agent work against real tools

   τ²-bench
   llama-3.1-8b-instant16.4%

   ministral-8b-latest26.6%

   ministral-8b-latest +10.2

4. Hard reasoning

   graduate-level science and multi-step analysis

   GPQA Diamond
   llama-3.1-8b-instant25.9%

   ministral-8b-latest47.1%

   ministral-8b-latest +21.2

Averaged over the benchmarks both models sat, llama-3.1-8b-instant returns 358.7 points of pass rate per dollar of blended price against 221.8 — 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.