Together benchmark: GLM-5.3 hits 87.6% on DeepSWE at ~$16, beating Fable 5
togethercompute · x · 2026-08-23
Together Compute reports that on DeepSWE, GLM-5.3 with up to four tries reaches an 87.6% solve rate for roughly $16, versus 69.7% at $21.63 for Fable 5 — beating it on both solve rate and total cost.
Related event: GLM-5.3 Beats Fable 5 on DeepSWE at Far Lower Cost(2 posts)→
More from coding & agent
- raylib 6.2 ships with 300+ improvements and 100 new contributors, 20 new API functions — jsuarez · 2026-10-16
- "Vibecoding" is as misleading a label as "AI" and "SI," dev complains — eschadiol · 2026-10-16
- Dev runs Pstack as a Grok bot to audit his own pipeline — it surfaces a pile of hidden bugs — alexcovo_eth · 2026-10-16
- Doc2Harness: New benchmark finds best coding agent passes only 53% across 329 cases — _akhaliq · 2026-10-16
- Perplexity open-sources SPACE, the Firecracker microVM sandbox behind Perplexity Computer — perplexity_ai · 2026-10-16
- Blackstone goes all-in on Factory for autonomous software development — matanSF · 2026-10-16