claude-fable-5 vs gpt-oss-120b

Capability for the money

Not the same tier: claude-fable-5 leads gpt-oss-120b by 32.7 points on tool use (τ²-bench), for 44.4× the price. They are level on following instructions (IFBench), so the premium only pays off on tool use work.

1. Following instructions

   extraction, classification, sticking to a format

   IFBench
   claude-fable-563.5%

   gpt-oss-120b69.0%

   gpt-oss-120b +5.5

2. Tool use

   multi-step agent work against real tools

   τ²-bench
   claude-fable-598.5%

   gpt-oss-120b65.8%

   claude-fable-5 +32.7

3. Hard reasoning

   graduate-level science and multi-step analysis

   GPQA Diamond
   claude-fable-592.6%

   gpt-oss-120b78.2%

   claude-fable-5 +14.4

Averaged over the benchmarks both models sat, gpt-oss-120b returns 157.8 points of pass rate per dollar of blended price against 4.2 — 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. No published coding score for one of these models, so that lens is omitted. And a benchmark is not your workload — it narrows the shortlist, it does not pick for you.