Cloud baseline

Opus 5 — 0.9755 on Gauntlet 5.2

us.anthropic.claude-opus-5 · scorer sb-5.2

Claude Opus 5Aug 17, 2026
Overall
0.9755
Hard
1.00
Excellent
yes
Benchmark
Gauntlet 5.2
Recorded duration
19m 30s

Token usage

Tokens: at least 2.1M in · 99.8k out (lower bound, harness session counters)

2,193,298 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. An earlier aborted attempt in the same folder (1,480,011 prompt / 39,913 completion) is not part of this build and is not counted.

  • us.anthropic.claude-opus-5

    In 2.1M · Out 99.8k · 63 calls

Tier breakdown

A · structure & runtime1.00
B · behaviour0.97
C · vendor contract1.00
D · finesse0.97

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%0.9860.591
A · Structure25% of core1.000.150
B · Behaviour30% of core0.970.174
C · Vendor contract25% of core1.000.150
D · Finesse20% of core0.970.117
Journey (J)15%0.9500.142
Visual (V)10%0.9170.092
Performance (P)5%1.0000.050
Hard blocks10%1.0000.100
Total0.9755

Run notes and corrections

Anthropic baseline — captured on the frozen v2 spec via AWS Bedrock, scored by the same sb-5.2 scorer as every community run.

Run details

Model
us.anthropic.claude-opus-5

How the benchmark is scored