Coding · sub-raceNarrow lead
Full-Stack Apps race
Shipping a working app end to end: schema, API, UI, auth and deployment config from a single brief.
- Leader
- Opus 5.5
- Margin
- 0.9 pts
- 1.1% ahead
- Weeks at #1
- 4
- in a row
- Changes
- 5
- 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 5.1Sonnet 5.5GPT-6.1 SolGPT-6 AstraKimi K3
Reigns at #1
Longest: Opus 4, 11 weeks (from May 2025).
Sibling races
More coding races
Why this race matters
This is what 'build me an app' really asks for, and where agentic builders live or die.
How it is scored
Share of apps passing end-to-end browser test suites.
Unit: percentHigher is betterPhoto finish under 0.5 ptsDominant over 3.0 pts
Data provenance
Full-stack app evals
Apps generated from a spec, scored by end-to-end browser tests.
Scores here are illustrative placeholders that mimic real benchmark patterns. Swap in live data through the score provider. Methodology