ox-alpha scores 58.4% on DeepSWE benchmark, matching Claude Opus 4.8
AccBalanced · x · 2026-08-23
A full end-to-end run of the 113-task DeepSWE benchmark on ox-alpha yielded a score of 58.4%, debunking the rumored 80% pass rate. This places it nearly identical to Claude Opus 4.8 (59%). Reviewers note it acts as a strong subagent with better vision and harness affinity for near-misses.
Related event: Ox Alpha scores ~63% on full DeepSWE; earlier 80% was subset artifact(6 posts)→
More from Models
- Google says teams across the company are using Gemini 4 Argon on its hardest engineering problems — CurieuxExplorer · 2026-10-15
- Perplexity's new embedding models: index with a 9B model, search with 0.6B — antoine_chaffin · 2026-10-15
- 797GB of n-gram counts in CPU RAM let 1B models match 57% more compute — PangWeiKoh · 2026-10-15
- Leak: Moonshot's Kimi flagship 'x4' done with pre-training, K3.1 in internal testing — lyraxana · 2026-10-15
- Unsloth ships GGUF quants for Nemotron 3.5: Bolt-74B runs in 24GB RAM — danielhanchen · 2026-10-15
- NVIDIA ships two open Nemotron 3.5 Bolt models: a 74B-A9B MoE and a mobile-friendly E4B — HankYeomans · 2026-10-15