specs at a glance
| Leaderboard rank | #5 of 28 |
|---|---|
| SWE-bench Verified | 95.4% |
| SWE-bench Pro | — |
| Terminal-Bench | 28.3 (TB3.0, vendor) |
| Input price / 1M | — |
| Output price / 1M | — |
| Context window | 1M |
| Open weights | No |
| Access | API (glm-5.3) · GLM Coding Plan · ZCode; weights promised ~2 weeks after launch |
| Maker | Z.ai (Zhipu AI) |
how good is GLM-5.3 at coding?
GLM-5.3 sits at #5 of 28 ranked models, posting 95.4% on SWE-bench Verified — 1.6 points behind #1 Claude Opus 5. Terminal-Bench (agentic terminal work): 28.3 (TB3.0, vendor).
Score provenance: Independent (vals.ai, 2026-08-20 sweep, mini-swe-agent bash-only harness): SWE-bench Verified 95.4% ±0.94, 6th of 86 systems. Left the verifying queue on 2026-08-20, six days after launch. Z.ai published NO SWE-bench Verified figure of its own, so this rank rests entirely on the independent run, which is the cleanest kind of row on this board. Read it as tied with GPT-5.6 Terra (95.4% ±0.94), Grok 4.6 (95.6%) and Claude Fable 5 (95.0%); pooled SEM is about 1.3 points and every gap is inside it. That result is striking given the release is post-training only, on the same base model as GLM 5.2, which is ranked far below on an independent 82.8%. Vendor numbers from the Aug 14 2026 release post, run mostly inside a Claude Code 2.1.207 harness at max effort rather than a neutral one: Terminal-Bench 3.0 28.3 (up from GLM-5.2’s 4.6), DeepSWE v1.1 66.9 (from 46.2), Agents’ Last Exam 28.5 (from 23.8). Its headline claims were cyber rather than coding: CyberGym 84.5% and ExploitBench 54.4%. Marked closed because the weights are NOT out: Z.ai said roughly two weeks after launch pending safety hardening, with no license announced, so the open-weights flag flips only when they actually land. See /p/glm-5-3-cybergym-open-weights-delayed/.
where can you use it?
Available via API (glm-5.3) · GLM Coding Plan · ZCode; weights promised ~2 weeks after launch. As a proprietary model, you're on the maker's infrastructure and release schedule.
head-to-head
Full storyGLM-5.3 tops CyberGym as Z.ai delays open weights two weeks
- Z.ai (Zhipu AI)vals.ai — SWE-bench Verified (independent)
Ranked on our AI Coding Leaderboard — scores confirmed against primary sources only, updated 2026-08-20.