SShogo Bench

Claude Opus 4.6 vs Claude Opus 5

Claude Opus 5 leads Claude Opus 4.6 by 12.2 points on the Shogo Agent Index. Claude Opus 4.6 wins 0 and Claude Opus 5 wins 17 of 17 shared benchmarks. Claude Opus 4.6 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 4.6Claude Opus 5
Agentic coding5774
Long-horizon autonomy6774
Knowledge-work agents4152
Computer use3956
Security & context learning5759

Shared benchmarks

BenchmarkClaude Opus 4.6Claude Opus 5
APEX-Agentsindex46.3%65.8%
Vending-Bench 2index$8,018$11,182
ARC-AGI94.0%97.5%
ARC-AGI-269.2%90.4%
Chess Puzzles21.0%43.0%
DTBench91.2%97.9%
FrontierCode26.6%53.4%
FrontierMath Tier 426.8%73.2%
FrontierMath Tiers 1-366.0%85.6%
GPQA Diamond90.5%93.9%
LMCA55.8%64.5%
MirrorCode33.3%87.8%
OTIS Mock AIME94.4%98.9%
ProofBench50.0%99.0%
SimpleBench67.6%80.6%
SimpleQA Verified47.0%59.9%
WebDev Arena15561687

Specs and price

Claude Opus 4.6Claude Opus 5
Agent Index53.2 (#31)65.4 (#11)
Agent $/M$2.31$2.31
Input / output $/M$5.00 / $25.00$5.00 / $25.00
Context1M1M
ReleasedFeb 5, 2026Jul 24, 2026
WeightsClosedClosed
API hosts56

Don’t pick one. Route.

Shogo can run Claude Opus 4.6 and Claude Opus 5 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo