China's Big-Tech Coding Agents vs Codex and Claude Code
ByteDance Trae, Tencent's CodeBuddy and WorkBuddy, Baidu Comate, Alibaba's Qwen Code and Qoder, Z.ai Zcode and DeepSeek Harness now match Codex and Claude Code on the feature surface. None has been independently measured on DeepSWE or Terminal-Bench, so AgentRanks does not rank them as reaching Codex/Claude Code level. This page separates what is verified from what is vendor marketing.
The reference bar
“Reaching Codex / Claude Code level” has a measured meaning here, not a vibes one.
| Reference | What it is | Score |
|---|---|---|
| Claude Code | Anthropic terminal agent, the AgentRanks architecture leader | 86 |
| ChatGPT Codex | OpenAI terminal agent, the second architecture slot | 84 |
| Claude Code + Fable 5 | Terminal-Bench 2.1 stack leader (agent harness + model together) | 83.8% |
A Chinese big-tech agent “reaches Codex / Claude Code level” only once it carries an AgentRanks architecture score near 84–86, or a Terminal-Bench stack score in the same band. Until then, feature parity is a product claim, not a ranking finding.
Star scale
What a star means, and where stars are withheld.
5★ = Opus 5 / Fable 5 measured level (Terminal-Bench frontier) · 1★ = basic. Coding-ability stars are withheld for every entry below: none has been independently measured on DeepSWE or Terminal-Bench, and that gap is the point of this page. Where a third-party editorial score exists (RECATOOLS /10), it is shown on each profile as a source-labelled bar — an editorial rating, not a benchmark.
Feature and benchmark comparison
Feature surface is real; the benchmark column is the gap. Click any name for its full profile.
| Agent | Vendor | Form | Agent / plan mode | MCP | ARscore | Users | Source |
|---|---|---|---|---|---|---|---|
| Claude Code | Anthropic | CLI/Desktop | Yes | Yes | 86 | not published | — |
| ChatGPT Codex | OpenAI | CLI/Desktop | Yes | Yes | 84 | not published | — |
| Trae | ByteDance | IDE + CLI | Builder + SOLO | Yes | not scored | 6M registered (first year) | Official |
| CodeBuddy | Tencent | IDE + plugin + CLI | Craft + Plan | Yes | not scored | not published | — |
| WorkBuddy | Tencent | Desktop workplace | Skills + automation | Yes | not scored | not published | — |
| Comate | Baidu | Plugin + IDE | Zulu | Yes | not scored | 7.6M developers (May 2025) | Official |
| Qwen CodeOS | Alibaba | CLI | — | — | 45 | open-source, GitHub-tracked | — |
| Qoder | Alibaba | IDE + CLI | Repo Wiki + Quest | Yes | not scored | not published | — |
| Zcode | Z.ai | Desktop ADE | Goal mode | Yes | not scored | not published | — |
| DeepSeek HarnessOS | DeepSeek | CLI + local web UI | Plugin kernel | plugin | not scored | ~169K GitHub stars | Marketplace |
User figures are vendor-reported unless marked Marketplace or Press, and none is independently audited. “Not scored” means the agent is outside the AgentRanks architecture rubric; it is not a low score.
Use-case capability matrix
Scenario coverage — presence, not benchmark performance.
| Agent | Local files | Docs / PPT | Excel reports | Analysis | Web search | Mini-programs | Web building |
|---|---|---|---|---|---|---|---|
| Trae | ✓ | — | — | ◐ | — | ✓ | ✓ |
| CodeBuddy | ✓ | ◐ | — | ◐ | — | ✓ | ✓ |
| WorkBuddy | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ◐ |
| Comate | ✓ | — | — | ◐ | — | ✓ | ✓ |
| Qwen Code | ✓ | — | — | — | — | — | ✓ |
| Qoder | ✓ | ◐ | ◐ | ◐ | — | ✓ | ✓ |
| Zcode | ✓ | ✓ | ? | ◐ | ✓ | ? | ✓ |
| DeepSeek Harness | ✓ | — | — | — | — | — | ✓ |
✓ supported · ◐ partial or via a sibling product (e.g. QoderWork CN, WorkBuddy Skills) · ? unclear · — not in scope. Click an agent name for per-scenario detail and official links.
Per-agent notes
What each entry ships, with its pricing tier and provenance.
| Agent | What it is | Pricing tier | Source |
|---|---|---|---|
| Trae | ByteDance's VS Code fork IDE with Builder + SOLO; open-source Trae-Agent CLI (MIT). | Free tier + $3 / $10 / $30 / $100 | RECATOOLS / Press |
| CodeBuddy | Tencent's coding arm (Buddy AI); first Chinese assistant with MCP; Code 2.0 added sub-agents. | Free / ¥99 / ¥199 / ¥999 | RECATOOLS / Press |
| WorkBuddy | Tencent's desktop workplace agent (Buddy AI); local files, PPT, Excel, web automation, Skills. | Free / ¥99 / ¥199 / ¥999 | Vendor (Bench) |
| Comate | Baidu's ERNIE assistant (June 2023); Zulu agent runs requirement-to-code; CAICT 4+ rated. | Free / Pro ¥55 | Official / CAICT |
| Qwen CodeOS | Alibaba's open-source CLI; the only scored Chinese big-tech entry (ARscore 45). | Free (open source) | AgentRanks |
| Qoder | Alibaba's first-party IDE (Aug 2025 preview; CN renamed from Tongyi Lingma 2026-05-20); Repo Wiki + Quest. | Pro $20 / $60 / $200 | RECATOOLS |
| Zcode | Z.ai's desktop ADE, official harness for GLM-5.2 / 5.3; Goal mode, multi-agent, remote control. | Client free; $18 / $72 / $160 | bitdoze / HN |
| DeepSeek HarnessOS | DeepSeek's MIT agent harness (Aug 13, 2026); Cordis plugin kernel; provider-agnostic. | Free (MIT); pay-per-token API | VentureBeat / GitHub |
Qwen Code vs Qoder: distinct Alibaba products, not the same tool renamed. Qwen Code is the open-source Qwen-first CLI (scored 45 here); Qoder is Alibaba’s first-party agentic IDE (Repo Wiki + Quest, multi-model routing, not scored). CodeBuddy vs WorkBuddy: Tencent’s Buddy AI splits coding (CodeBuddy, IDE+CLI) from workplace (WorkBuddy, desktop files/PPT/Excel/automation); the two share one credit account.
The honest verdict
Feature parity is real; benchmark parity is unproven.
The eight Chinese big-tech entries ship the same agentic surface that defines Codex and Claude Code in 2026: multi-file generation, plan-first execution, MCP for external tools, and a CLI or IDE path. On features, they are in the conversation. On benchmarks, they are not: none publishes or has been independently measured on DeepSWE or Terminal-Bench 2.1, so AgentRanks cannot place any of them next to Codex (84) or Claude Code (86). “Reaching Codex / Claude Code level” is, for now, a vendor-marketing claim rather than a ranking finding — it becomes a finding the day one of them is scored.
Compare further
Reference agents and the scored Chinese entry.