Coding · sub-raceNarrow lead
Backend & APIs race
Services, APIs, databases, auth and business logic, graded by hidden test suites.
- Leader
- Opus 5.5
- Margin
- 1.0 pts
- 1.2% ahead
- Weeks at #1
- 4
- in a row
- Changes
- 7
- in 2026
Warming up the track…
Oct 19, 2026Opus 5.5 leads
2025Apr ’25Jul ’25Oct ’252026Apr ’26Jul ’26Oct ’26
Score history
Top 6 today over the leader's frontier · click to jump to a week
#1 frontierOpus 5.5Fable 5.1GPT-6 AstraSonnet 5.5GPT-6.1 SolGemini 4 Argon
Reigns at #1
Longest: Opus 4, 11 weeks (from May 2025).
Sibling races
More coding races
Why this race matters
Most production code is unglamorous server logic. Correctness here is what keeps systems running.
How it is scored
Share of back-end tasks passing hidden unit and integration tests.
Unit: percentHigher is betterPhoto finish under 0.5 ptsDominant over 3.0 pts
Data provenance
Hard exercises across six languages.
BaxBench-style suites
Back-end correctness and security tests.
Scores here are illustrative placeholders that mimic real benchmark patterns. Swap in live data through the score provider. Methodology