{"id":51221162,"url":"https://github.com/QuesmaOrg/otel-bench","last_synced_at":"2026-07-16T17:01:02.176Z","repository":{"id":332753877,"uuid":"1134215158","full_name":"QuesmaOrg/otel-bench","owner":"QuesmaOrg","description":"OpenTelemetry Benchmark - can AI trace your failed login?","archived":false,"fork":false,"pushed_at":"2026-03-01T18:56:20.000Z","size":546,"stargazers_count":19,"open_issues_count":2,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-16T11:00:10.622Z","etag":null,"topics":["ai-agents","benchmark","opentelemetry"],"latest_commit_sha":null,"homepage":"https://quesma.com/benchmarks/otel/","language":"Shell","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/QuesmaOrg.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-01-14T12:13:39.000Z","updated_at":"2026-04-08T04:35:52.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/QuesmaOrg/otel-bench","commit_stats":null,"previous_names":["quesmaorg/otel-bench"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/QuesmaOrg/otel-bench","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/QuesmaOrg%2Fotel-bench","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/QuesmaOrg%2Fotel-bench/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/QuesmaOrg%2Fotel-bench/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/QuesmaOrg%2Fotel-bench/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/QuesmaOrg","download_url":"https://codeload.github.com/QuesmaOrg/otel-bench/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/QuesmaOrg%2Fotel-bench/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35551282,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-16T02:00:06.687Z","response_time":83,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-agents","benchmark","opentelemetry"],"created_at":"2026-06-28T07:04:36.587Z","updated_at":"2026-07-16T17:01:02.170Z","avatar_url":"https://github.com/QuesmaOrg.png","language":"Shell","funding_links":[],"categories":["Evaluation Benchmarks"],"sub_categories":[],"readme":"# OpenTelemetry Benchmark (OTelBench) by Quesma\n\nAn open-source benchmark for evaluating AI models on OpenTelemetry instrumentation tasks across multiple programming languages.\n\n* Benchmark: [OTelBench results](https://quesma.com/benchmarks/otel/)\n* Blog post: [Benchmarking OpenTelemetry: Can AI trace your failed login?](https://quesma.com/blog/introducing-otel-bench/)\n\n## Quick start\n\nRequires [Harbor](https://harborframework.com) (`uv tool install harbor`), Docker, and relevant API KEYs.\n\nBy default, we use the `terminus-2` agent (default for Harbor) via [OpenRouter](https://openrouter.ai/) to compare models.\nYou are free to use others, including well-known CLI AI Agents like Claude Code, Codex, or Cursor CLI.\n\nYou need to clone this repo:\n\n```bash\ngit clone git@github.com:QuesmaOrg/otel-bench.git\ncd otel-bench\n```\n\nRun a single task, for a single model:\n\n```bash\nexport ANTHROPIC_API_KEY=...\nharbor run \\ \n  --path datasets/otel \\ \n  --task-name cpp-simple \\ \n  --agent terminus-2\n  --model anthropic/claude-opus-4-5-20251101\n```\n\nTask names allow wildcards, so if you want to run all Go tasks, it works like:\n\n```bash\nexport OPENAI_API_KEY=...\nharbor run \\ \n  --path datasets/otel \\ \n  --task-name go-* \\ \n  --agent terminus-2 \\ \n  --model openai/gpt-5.2\n```\n\nRun all tasks with a few models, with 3 attempts per model-task combination:\n\n```bash\nexport OPENROUTER_API_KEY=...\nharbor run \\ \n  --path datasets/otel \\ \n  --agent terminus-2 \\ \n  --model openrouter/google/gemini-3-pro-preview \\ \n  --model openrouter/anthropic/claude-opus-4-5 \\ \n  --model openrouter/openai/gpt-5.2-codex \\ \n  --n-attempts 3\n```\n\nYou can view trajectories (interactions between the agent and the system) via `harbor view jobs`.\nOur overview of Harbor in [Migrating CompileBench to Harbor: standardizing AI agent evals](https://quesma.com/blog/compilebench-in-harbor/).\n\n## Content\n\nThe OpenTelemetry dataset [datasets/otel](./datasets/otel) contains a set of tasks testing AI models' ability to instrument applications with OpenTelemetry across 11 programming languages.\nSo far, it contains the following tasks:\n\n* **C++**: [simple](https://quesma.com/benchmarks/otel/tasks/cpp-simple), [advanced](https://quesma.com/benchmarks/otel/tasks/cpp-advanced), [distributed-context-propagation](https://quesma.com/benchmarks/otel/tasks/cpp-distributed-context-propagation)\n* **Go**: [http-tracing](https://quesma.com/benchmarks/otel/tasks/go-http-tracing), [distributed-context-propagation](https://quesma.com/benchmarks/otel/tasks/go-distributed-context-propagation), [workflow-tracing](https://quesma.com/benchmarks/otel/tasks/go-workflow-tracing), [microservices](https://quesma.com/benchmarks/otel/tasks/go-microservices), [grpc-fix](https://quesma.com/benchmarks/otel/tasks/go-grpc-fix), [microservices-logs](https://quesma.com/benchmarks/otel/tasks/go-microservices-logs), [microservices-traces](https://quesma.com/benchmarks/otel/tasks/go-microservices-traces), [microservices-traces-simple](https://quesma.com/benchmarks/otel/tasks/go-microservices-traces-simple)\n* **Java**: [simple](https://quesma.com/benchmarks/otel/tasks/java-simple), [advanced](https://quesma.com/benchmarks/otel/tasks/java-advanced), [distributed-context-propagation](https://quesma.com/benchmarks/otel/tasks/java-distributed-context-propagation), [microservices](https://quesma.com/benchmarks/otel/tasks/java-microservices)\n* **JavaScript**: [microservices](https://quesma.com/benchmarks/otel/tasks/js-microservices)\n* **.NET**: [microservices](https://quesma.com/benchmarks/otel/tasks/net-microservices)\n* **PHP**: [distributed-context-propagation](https://quesma.com/benchmarks/otel/tasks/php-distributed-context-propagation), [microservices](https://quesma.com/benchmarks/otel/tasks/php-microservices)\n* **Python**: [distributed-context-propagation](https://quesma.com/benchmarks/otel/tasks/python-distributed-context-propagation), [microservices](https://quesma.com/benchmarks/otel/tasks/python-microservices)\n* **Ruby**: [microservices](https://quesma.com/benchmarks/otel/tasks/ruby-microservices)\n* **Rust**: [distributed-context-propagation](https://quesma.com/benchmarks/otel/tasks/rust-distributed-context-propagation), [microservices](https://quesma.com/benchmarks/otel/tasks/rust-microservices)\n* **Erlang**: [microservices](https://quesma.com/benchmarks/otel/tasks/erlang-microservices)\n* **Swift**: [microservices](https://quesma.com/benchmarks/otel/tasks/swift-microservices)\n\n## Notes\n\n* Tasks are internet dependent and require internet access to run\n* Task solution instructions are not yet included (work in progress)\n* Results are in [benchmark-results/otel](./benchmark-results/otel), for reference and comparison - we generate these from `jobs` (so far pipeline is no included).\n\n## License\n\nApache 2.0, see [LICENSE](LICENSE) for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FQuesmaOrg%2Fotel-bench","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FQuesmaOrg%2Fotel-bench","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FQuesmaOrg%2Fotel-bench/lists"}