SShogo Bench

Claude Opus 4.8 vs Claude Opus 5.5

Claude Opus 5.5 leads Claude Opus 4.8 by 14.6 points on the Shogo Agent Index. Claude Opus 4.8 wins 0 and Claude Opus 5.5 wins 21 of 21 shared benchmarks. Claude Opus 5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 4.8Claude Opus 5.5
Agentic coding6381
Long-horizon autonomy6676
Knowledge-work agents4358
Computer use4766
Security & context learning5562

Shared benchmarks

BenchmarkClaude Opus 4.8Claude Opus 5.5
APEX-Agentsindex48.9%73.5%
Vending-Bench 2index$5,787$9,235
Remote Labor Indexindex8.3%21.3%
PostTrainBenchindex31.0%43.8%
ARC-AGI92.5%98.5%
ARC-AGI-272.1%93.3%
Chess Puzzles52.0%67.0%
CritPt20.9%31.7%
DTBench94.9%98.9%
FrontierCode46.5%54.6%
FrontierMath Tier 456.1%95.0%
FrontierMath Tiers 1-380.0%91.2%
GPQA Diamond91.0%94.1%
LMCA57.5%68.2%
MirrorCode65.6%95.6%
OTIS Mock AIME98.3%100.0%
ProofBench69.0%100.0%
SciCode53.5%66.9%
SimpleBench64.8%88.4%
SimpleQA Verified53.0%72.2%
WebDev Arena15591820

Specs and price

Claude Opus 4.8Claude Opus 5.5
Agent Index56.3 (#20)70.9 (#3)
Agent $/M$2.31$1.69
Input / output $/M$5.00 / $25.00$4.00 / $20.00
Context1M1M
ReleasedMay 28, 2026Sep 22, 2026
WeightsClosedClosed
API hosts66

Don’t pick one. Route.

Shogo can run Claude Opus 4.8 and Claude Opus 5.5 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo