Automated daily benchmark runs across Claude Code, Codex CLI, and Cursor Agent
Benchmark Sessions
737
Vendor Observations
1331
Platforms
What kinds of help developers seek — classified from prompt text
35
6
Postgres, serverless DBs, vector search, branching
AI agent frameworks, orchestration, tool ecosystems
Build pipelines, deployment automation, preview environments
Edge runtimes, serverless functions, CDN compute
Error tracking, crash reporting, alerting
Feature management, A/B testing, rollouts
LLM tracing, prompt analytics, cost tracking
APM, distributed tracing, metrics, logging
Secret rotation, env var management, vaults
SAST, dependency scanning, container security
API docs, developer experience, documentation
On-call, incident response, status pages
Multi-domain prompts spanning several tool categories
| Vendor | Claude Code | Codex CLI | Cursor | Total |
|---|---|---|---|---|
| Sentry | 87 | 25 | 2 | 114 |
| GitHub Actions | 69 | 38 | 4 | 111 |
| Supabase | 47 | 23 | 5 | 75 |
| Neon | 56 | 13 | 2 | 71 |
| Datadog | 49 | 12 | 3 | 64 |
| Port | 22 | 11 | 20 | 53 |
| Doppler | 30 | 9 | 2 | 41 |
| PagerDuty | 27 | 11 | 2 | 40 |
| Honeycomb | 30 | 8 | 1 | 39 |
| Grafana | 26 | 9 | 1 | 36 |
| Cloudflare Workers | 21 | 12 | 2 | 35 |
| AWS Secrets Manager | 24 | 8 | 1 | 33 |
| HashiCorp Vault | 22 | 9 | 2 | 33 |
| Upstash | 22 | 7 | 1 | 30 |
| Infisical | 20 | 9 | - | 29 |
| Fly.io | 17 | 6 | 5 | 28 |
| Langfuse | 15 | 10 | 2 | 27 |
| Turso | 16 | 9 | 2 | 27 |
| LaunchDarkly | 17 | 6 | 3 | 26 |
| PlanetScale | 21 | 4 | 1 | 26 |
| Braintrust | 13 | 10 | 1 | 24 |
| LangSmith | 13 | 11 | - | 24 |
| Statsig | 15 | 7 | 1 | 23 |
| New Relic | 18 | 4 | - | 22 |
| Backstage | 16 | 5 | - | 21 |
| Snyk | 13 | 7 | 1 | 21 |
| Rollbar | 14 | 3 | 1 | 18 |
| Bugsnag | 12 | 4 | 1 | 17 |
| Flagsmith | 10 | 5 | - | 15 |
| Semgrep | 10 | 5 | - | 15 |
| Session | Platform | Model | Observations | Vendors | Date |
|---|---|---|---|---|---|
| 762f93eb-d7a... | Claude Code | <synthetic> | 0 | - | 2026-02-18 |
| 969e3cfc-737... | Claude Code | - | 0 | - | 2026-02-18 |
| 02df5d9c-76e... | Claude Code | <synthetic> | 0 | - | 2026-02-18 |
| 611ca563-adf... | Claude Code | - | 0 | - | 2026-02-18 |
| e77f3732-42f... | Claude Code | <synthetic> | 0 | - | 2026-02-18 |
| 55003e4d-105... | Claude Code | - | 0 | - | 2026-02-18 |
| a9dce73f-6a7... | Claude Code | <synthetic> | 0 | - | 2026-02-18 |
| dbd119d5-78f... | Claude Code | - | 0 | - | 2026-02-18 |
| 16d76376-96c... | Claude Code | <synthetic> | 0 | - | 2026-02-18 |
| 2b762e18-267... | Claude Code | - | 0 | - | 2026-02-18 |
| 85b04f7c-24c... | Claude Code | <synthetic> | 0 | - | 2026-02-18 |
| 3a57e8e0-e55... | Claude Code | - | 0 | - | 2026-02-18 |
| df5a0a49-fa5... | Claude Code | <synthetic> | 0 | - | 2026-02-18 |
| 57769600-ed3... | Claude Code | - | 0 | - | 2026-02-18 |
| ba791ea2-07a... | Claude Code | <synthetic> | 0 | - | 2026-02-18 |
| d6cbab19-0e5... | Claude Code | - | 0 | - | 2026-02-18 |
| 30149c8e-f7f... | Claude Code | <synthetic> | 0 | - | 2026-02-18 |
| 682bf1b5-9f8... | Claude Code | - | 0 | - | 2026-02-18 |
| 5d44d598-b94... | Claude Code | <synthetic> | 0 | - | 2026-02-18 |
| 9e525b9f-796... | Claude Code | - | 0 | - | 2026-02-18 |
| fc63cfc2-b7a... | Claude Code | <synthetic> | 0 | - | 2026-02-18 |
| 0d1c4cc8-c31... | Claude Code | - | 0 | - | 2026-02-18 |
| 889525a5-e2b... | Claude Code | <synthetic> | 0 | - | 2026-02-18 |
| 4d12fb7a-4f5... | Claude Code | - | 0 | - | 2026-02-18 |
| 650899b9-ca9... | Claude Code | <synthetic> | 0 | - | 2026-02-18 |
| 263d4251-8bb... | Claude Code | - | 0 | - | 2026-02-18 |
| 243842f9-9d5... | Claude Code | <synthetic> | 0 | - | 2026-02-18 |
| 3cbd10c4-53b... | Claude Code | - | 0 | - | 2026-02-18 |
| ab85734f-50a... | Claude Code | <synthetic> | 0 | - | 2026-02-18 |
| a32da845-da7... | Claude Code | - | 0 | - | 2026-02-18 |
| 7b45ff4d-bc6... | Claude Code | <synthetic> | 0 | - | 2026-02-18 |
| e0442328-301... | Claude Code | - | 0 | - | 2026-02-18 |
| 785635be-cc3... | Claude Code | <synthetic> | 0 | - | 2026-02-18 |
| 70dc856b-572... | Claude Code | - | 0 | - | 2026-02-18 |
| 8c5b9d44-572... | Claude Code | <synthetic> | 0 | - | 2026-02-18 |
| c19ed27d-b70... | Claude Code | - | 0 | - | 2026-02-18 |
| 1e327262-ffc... | Claude Code | <synthetic> | 0 | - | 2026-02-18 |
| b4248331-dbb... | Claude Code | - | 0 | - | 2026-02-18 |
| 1a350723-9cd... | Claude Code | <synthetic> | 6 | backstage,cortex,datadog,opslevel,pagerduty,port | 2026-02-18 |
| f308a80e-fd1... | Claude Code | - | 6 | backstage,cortex,datadog,opslevel,pagerduty,port | 2026-02-18 |
| b66d93f2-b3c... | Claude Code | claude-sonnet-4-5-20250929 | 12 | backstage,cortex,datadog,github-actions,grafana,opslevel,pagerduty,port | 2026-02-18 |
| dcee60c1-5eb... | Claude Code | - | 8 | backstage,cortex,datadog,github-actions,grafana,opslevel,pagerduty,port | 2026-02-18 |
| 7ecb3ec1-ed1... | Claude Code | claude-sonnet-4-5-20250929 | 11 | aws-secrets-manager,datadog,doppler,github-actions,hashicorp-vault,infisical,port | 2026-02-18 |
| a219fa98-b69... | Claude Code | - | 7 | aws-secrets-manager,datadog,doppler,github-actions,hashicorp-vault,infisical,port | 2026-02-18 |
| 78f134ab-1f6... | Claude Code | claude-sonnet-4-5-20250929 | 4 | aws-secrets-manager,doppler,github-actions,infisical | 2026-02-18 |
| e219af9b-023... | Claude Code | - | 4 | aws-secrets-manager,doppler,github-actions,infisical | 2026-02-18 |
| 141c0f6d-42f... | Claude Code | claude-sonnet-4-5-20250929 | 9 | datadog,doppler,github-actions,hashicorp-vault,infisical,railway-deployments | 2026-02-18 |
| 1571839f-ad2... | Claude Code | - | 6 | datadog,doppler,github-actions,hashicorp-vault,infisical,railway-deployments | 2026-02-18 |
| 06008df0-598... | Claude Code | claude-sonnet-4-5-20250929 | 2 | flagsmith,unleash | 2026-02-18 |
| 88cc1393-6fe... | Claude Code | - | 2 | flagsmith,unleash | 2026-02-18 |