Remix.run Logo
jaen 2 days ago

For similarly sized models, not looking very good on the slightly-less-benchmaxxed Terminal-Bench 2.0:

  Laguna XS.2  33B-A3B params: 30.6
  Qwen 3.6     35B-A3B       : 51.5
  Devstral 2   123B          : 31.2
Quite a huge lead for Qwen... well, at least it's catching up to other smaller Western labs.
megavon 2 days ago | parent [-]

Need to look at SWEBench-Pro, it's super competitive. Suspect they'll catch up given the longer-tail on TB scores.

jaen 2 days ago | parent [-]

Just by the (lack of) inter-model variance, I don't think SWEBench-Pro does a very good job of representing model capability. Terminal-Bench seems more challenging and separates the wheat from the chaff.

Also, *ops work, which in my experience can actually be more complicated than SWE is underrepresented there obviously.