Cloud baseline

Opus 5 — 0.9142 on Gauntlet 5.3

us.anthropic.claude-opus-5 · scorer sb-5.3

Claude Opus 5Aug 18, 2026
Overall
0.9142
Hard
1.00
Excellent
yes
Benchmark
Gauntlet 5.3

Token usage

Tokens: at least 5.7M in · 38.5k out (lower bound, harness session counters)

5,786,301 tokens over 63 model calls: every call of the run, the model's own and the harness's helper calls, counted from harness session counters. These are a lower bound.

The harness's session counters for this run (the usage AWS Bedrock returned per response, summed); calls counted from the stored transcript (approximate). Prompt caching was off on Bedrock for Claude then, so no cached tokens. Bedrock keeps no per-call bill to query. Matched to build r0 by its score (the build the sb-5.3 board pins); medium confidence in that match.

  • us.anthropic.claude-opus-5

    In 5.7M · Out 38.5k · 63 calls

Tier breakdown

A · structure & runtime1.00
B · behaviour1.00
C · vendor contract0.90
D · finesse0.88

Scoring detail

How this score was built

Per-check scorer output, as posted by the app. Expand a section to inspect its checks.

ComponentWeightEarnedPoints
Core (tiers A–D)60%0.9500.570
A · Structure25% of core1.000.150
B · Behaviour30% of core1.000.180
C · Vendor contract25% of core0.900.135
D · Finesse20% of core0.880.105
Journey (J)15%0.9500.142
Visual (V)10%0.5170.052
Performance (P)5%1.0000.050
Hard blocks10%1.0000.100
Total0.9142

Run notes and corrections

Anthropic baseline — the frozen v2 spec build, rescored by the sb-5.3 scorer. Screenshots are the scorer's own render-gate captures of the built app.

Screenshots

Recorded views of the built application. Captions identify the available captures; the number of images does not imply a number of repair rounds.

1First render — before repairs
2Final render
3After sync
4Mobile · 375px

Run details

Model
us.anthropic.claude-opus-5

How the benchmark is scored