SWE-bench Verified ↗
Repository issue repair and test outcomes.
Compare the same agent scaffold, version, tools, and budget. An English repository task does not measure Chinese instruction following.
Workflow · Coding
Compare coding benchmarks, their limits, and a repeatable Chinese-language repository trial. Inspect actual run coverage before choosing an AI coding agent.
16 catalog tools. Catalog scores help browse candidates; inspect detail pages for review status, source versions, and dates.
Use repository repair, code editing, and algorithm benchmarks for different questions. Then compare candidates on the same Chinese-language task in your own repository. A model score alone does not establish an agent’s quality in your workflow.
Editorial selection method · sources checked . These sources are not new OKCodex measured results.
Repository issue repair and test outcomes.
Compare the same agent scaffold, version, tools, and budget. An English repository task does not measure Chinese instruction following.
Code generation, self-repair, execution, and test-output prediction with time-based problem releases.
Record the problem release, scenario, and sampling settings. Algorithm tasks do not establish multi-file repository delivery.
Code editing in the Aider workflow, with test outcomes and run details.
This is maintained by the tool’s project, not an independent audit of every agent. Check model version, edit format, attempts, and cost conditions.
Benchmark limits matter: OpenAI’s February 2026 analysis reports test and contamination problems in SWE-bench Verified. Treat historical scores cautiously and cross-check fresh tasks; no single leaderboard establishes the best coding agent. Read the original analysis ↗
The figures below are site-wide benchmark totals, not coding-only results or a comparison of every tool in this category. Inspect the task and output for each run.
10 verified runs cover 1 catalog entry.
Actual run versions: deepseek-v4-flash; latest completed run:
Run count is not a count of tested products. Catalog entries and source reviews do not establish measured performance or a multi-product benchmark.
Automatic reviews analyze public sources, not hands-on tests. Manual publication also requires separate run evidence before a performance claim.
Inspect tasks, outputs and actual run models →Example tasks to start your selection. Recommendations stay in this category; verify candidate capabilities through sources or a trial.
Filter by budget and language · Submit an unresolved selection need
Cursor
The AI IDE with the strongest coding capabilities, putting Claude Opus 4.8 + GPT-5.5 into your editor
Claude
Anthropic's AI assistant for drafting, editing and analyzing text.
GitHub Copilot
The earliest and most widely adopted AI coding assistant, deeply integrated with GitHub workflows
v0 by Vercel
Natural language generates runnable React UI, the fastest path to front-end prototypes
Dify
Open-source LLM application development platform, 100K+ GitHub Stars, self-hosted with zero lock-in
Qwen3.7-Max
Alibaba Cloud Tongyi Qianwen Flagship Edition: Million-Token Context + Ultra-Long-Horizon Agent Execution
Windsurf
Agentic IDE: Cascade-centric automated coding, Cursor's main rival
LiveKit Agents
A framework for building real-time multimodal AI applications
智谱清言 GLM-5
Chinese-language Agent with a Tsinghua technology background, GLM-5.2 one-million-token context, capabilities benchmarked against Opus 4.8
Supermemory
A self-hostable long-term memory layer for AI applications and agents
gstack
AI-powered full-stack application generator
MathCode
Math coding agent that automatically generates and verifies solution code
OpenSpec
AI-driven technical specification generation tool
semantica-agi/semantica
Semantics-driven autonomous agent framework
DeepSeek API
Provides function calling, JSON output and streaming output through a developer model API
Ollama Local Inference
Supports offline inference with prepared local models and your own compute