OpenAI — Engineering Performance
Avg. perf / dev / mo (ETV)
+10.8%
5.45 → 6.03
Active contributors
−15.8%
38.0 → 32.0
Growth
−9.2pp
46.6% → 37.4%
Fixes
−1.9pp
12.7% → 10.8%
OpenAI vs. 500 OSS Performance Index
Per-engineer ETV for OpenAI plotted against the pooled 500 OSS Performance Index. Both series are 90-day trailing rolling averages scaled to a 30-day month, so the curves sit on the same scale (ETV / dev / mo) and can be compared point-for-point. Latest reading: OpenAI is 206% above the index (6.02 vs 1.97 ETV/dev/mo). Baseline gap was 0% above.
Monthly reports
Highlights
- Enhanced *OpenAI.Conversations* and *OpenAI.Containers* with new models, CRUD operations, and advanced resource management features ([ec5f6014 · Jose Arriaga Maldonado], [71ed8ef9 · Jose Arriaga Maldonado]).
- Introduced robust *prompt caching* for *OpenAI.Responses* and in-memory caching for *Codex Apps tools*, significantly boosting performance and efficiency ([1861ebb8 · Jose Arriaga Maldonado], [703793c2 · Owen Lin]).
- Expanded *model capabilities* by adding GPT-5.6 variants to the *Amazon Bedrock* catalog and enabling provider-aware model fallback for `thread/start` API ([69596f0e · Celia Chen], [6d9dbacf · Celia Chen]).
- Improved *system stability* and *modularity* through features like pinning *MCP runtimes* to model steps, allowing extensions to contribute *World State* sections, and stabilizing IDs for synthesized call outputs ([ee9e0f63 · jif], [c9e6d978 · jif], [d2885dc3 · Michael Bolin]).
- Refactored *release processes* for `zsh` artifacts, streamlining dependencies and improving independent versioning ([e23e7cbe · Michael Bolin], [891f1f4c · Michael Bolin]).
Observations
- Overall development activity saw a notable decrease across all metrics compared to the 5-month average: total output was 135 vs 188 (-28%), grow score was 53 vs 82 (-36%), and commit volume was 504 vs 737 (-32%).
- The *waste score* experienced a significant 48% reduction, dropping to 11 from the 5-month average of 21, indicating a strong focus on quality and reduced rework.
- Multiple commits ([82e583cc · Kazuhiro Sera], [7713342b · Kazuhiro Sera], [85670fa3 · Kazuhiro Sera], [81fe6ab3 · Kazuhiro Sera], [33219675 · Kazuhiro Sera], [4a9d7518 · Kazuhiro Sera]) indicate ongoing, iterative refinement of the *maintainer-review skill*, suggesting continuous improvement in code review processes.
- Several critical bug fixes were categorized as waste, including a fix for *OpenAI agents' conversation memory* ([75bf1dfc · Jianke LIN]), a data integrity bug for `thread.history_mode` immutability ([812cd2bb · Owen Lin]), and a security fix for *Realtime agent* logging ([8c688b96 · Minh Vu]).
- A significant update to the `@typespec/http-client-csharp` generator and *OpenAI SDK* regeneration for `multipart/form-data` was marked as waste ([3b4890eb · github-actions[bot]]), potentially indicating challenges or rework during this complex integration.
- The *Managed Capability Protocol (MCP) runtime management* and *World State* mechanisms were areas of high activity, with multiple commits addressing stability, performance, and modularity, such as reusing MCP runtimes ([6d2168f0 · jif]) and projecting executor skills through *World State* ([5eebeb81 · jif]).
Repositories
Active repositories ranked by average performance per developer per month (over the last 90 days). The chart shows monthly performance composition — each repo as a stacked layer, with the top of the stack representing total org performance per month. Top 7 repos shown; the remainder is aggregated as “Other”.
| Repository | ||||
|---|---|---|---|---|
| openai-agents-js | 1 | 39 | 12.9 | +942%since Q2 2025 |
| openai-agents-python | 1 | 24 | 8.0 | +532%since Q2 2025 |
| codex | 26 | 509 | 6.5 | +1367%since Q2 2025 |
| openai-dotnet | 3 | 7 | 0.7 | +311%since Q2 2025 |
| plugins | 2 | 1 | 0.2 | — |
| openai-node | 1 | 0 | 0.0 | −100%since Q2 2025 |
Company total6 repositories | 32unique devs | 579ETV total | 6.03ETV / dev / mo | +1124%since Q2 2025 |
| Performance (ETV) is the sum of every repository above. Active devs at the company level counts unique contributors across all repos, so a contributor working in multiple repos is counted once here but appears in each repo's row (the per-repo column will sum higher). ETV / dev / mo = Company ETV ÷ unique devs ÷ 3 mo. The "Since start" column compares each repo's Q1 2026 quarterly performance to the first quarter it had any activity — for repos that existed in Q2 2025 (when this index began), that's Q2 2025; for younger repos it's the quarter they actually started. The company row uses Q2 2025 as the baseline since the index itself began then. | ||||
Performance Growth vs Active Contributors
Engineering performance is outpacing team growth by 14.2×. Left axis shows total performance score, right axis shows active contributor count. The gap between curves represents productivity gains — more delivered per person, not just more people. Unit: Engineering Throughput Value (ETV).
Cost per Performance Unit
−85%
If performance per engineer more than doubled, each unit of engineering performance now costs approximately 85% less than at the baseline 90-day window (ending 2025-06-29). This is a directional estimate — the exact figure depends on fully-loaded engineer cost, but the direction is unambiguous.
Effective Capacity Added
+186 engineers
At today's productivity, the current 32-person team delivers the performance equivalent of 218 engineers at the baseline 90-day rolling window (ending 2025-06-29). That's roughly 186 engineers worth of capacity added through productivity gains, not hiring.
Performance Composition
Stacked bars show total complexity performance split into Growth (new value), Maintenance (sustaining systems), and Fixes (rework). The yellow line overlays performance per contributor — rising line means each engineer is delivering more, regardless of team size changes. Unit: Engineering Throughput Value (ETV).
CapEx vs OpEx
Monthly CapEx vs OpEx split. CapEx (capitalizable investment) is Growth — new features and capabilities. OpEx (operating expense) is Maintenance plus Fixes — keeping the lights on and reworking what's already shipped. The yellow line is the CapEx share, a quick read on how much of the month went into building new vs sustaining existing. Unit: Engineering Throughput Value (ETV).
Hours per Repository
Trailing 90-day window (64 working days). Org-level capacity is allocated to each repo by its share of org performance, then split CapEx / OpEx by that repo's own Growth vs Maintenance + Fixes mix.
| codex | 39.8% | 60.2% |
| openai-dotnet | 32.1% | 67.9% |
| openai-agents-js | 24.2% | 75.8% |
| plugins | 20.0% | 80.0% |
| openai-agents-python | 9.3% | 90.7% |
| openai-node | 0.0% | 0.0% |
| Total | 37.3% | 62.7% |
Fix Burden Distribution
Monthly rework volume broken down by who did it. Top contributors carry their named slice; everyone else is rolled into Others. Use this to spot whether fix work is concentrated on a small group (bus-factor risk) or distributed across the team.
Quarterly Summary
The raw numbers behind the charts: commits analyzed, active contributors, total performance, performance per developer, and the Growth / Maintenance / Fixes split for each quarter.
| Quarter | ||||||||
|---|---|---|---|---|---|---|---|---|
| Q2'25 | 448 | 18 | 47.99 | 0.9 | 52.8% | 35.2% | 12% | — |
| Q3'25 | 1,092 | 25 | 160.91 | 2.1 | 43.2% | 45.8% | 11% | +235% |
| Q4'25 | 1,096 | 32 | 198.11 | 2.1 | 46.7% | 42.5% | 10.8% | +23% |
| Q1'26 | 2,507 | 38 | 587.59 | 5.2 | 46.9% | 40.3% | 12.8% | +197% |
Top Contributors
Contributors ranked by performance per month (Growth + Maintenance + Fixes), over the last 90 days normalized to a 30-day calendar month.
The best way to measure AI efficiency
SampleA preview of the Navigara engine running on a sample organization. The numbers below are illustrative, not part of the OSS500 benchmark above.
Measure
Score every commit by depth
GitHub commits are weighted by what it took to write them, not by lines of code. The result is ETV per developer per month.
SourceGitHub
Spend
Tie ETV to cost
AI token bills and seat costs are pulled per team and divided by the ETV produced. The result is your true cost per unit of work.
SourceToken usage + finance
Map
Tie work to objectives
Each ETV is mapped to your Jira epics and labels, so you can see what's key-aligned, aligned, or unmapped capacity.
SourceJira
Performance
ETV delivered per developer / month
9.4ETV / dev / month
5.6 below target- Non-AI 5.8
- AI 3.6
AI Efficiency
AI spend per ETV unit delivered
$4.20
$0.60 over target- Cost / ETV $4.20
Objective Alignment
Share of work mapped to key objectives
51%
24 pts below target- Key-aligned 28%
- Aligned 23%