SShogo Bench

Claude Opus 4.7 vs Claude Opus 5

Claude Opus 5 leads Claude Opus 4.7 by 10.8 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Opus 4.7 wins 0 and Claude Opus 5 wins 21 of 21 shared benchmarks. Claude Opus 4.7 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 4.7Claude Opus 5
Agentic coding6074
Long-horizon autonomy6974
Knowledge-work agents4152
Computer use4456
Security & context learning5259

Shared benchmarks

BenchmarkClaude Opus 4.7Claude Opus 5
APEX-Agentsindex49.2%65.8%
OSWorld 2.0index18.2%31.4%
Vending-Bench 2index$10,937$11,182
PostTrainBenchindex24.3%35.7%
ARC-AGI93.5%97.5%
ARC-AGI-275.8%90.4%
Chess Puzzles41.0%43.0%
CritPt12.0%29.1%
DTBench94.7%97.9%
FrontierCode38.5%53.4%
FrontierMath Tier 431.7%73.2%
FrontierMath Tiers 1-370.2%85.6%
GPQA Diamond90.2%93.9%
LMCA52.2%64.5%
MirrorCode43.3%87.8%
OTIS Mock AIME97.8%98.9%
ProofBench54.0%99.0%
SciCode54.5%56.4%
SimpleBench61.7%80.6%
SimpleQA Verified51.7%59.9%
WebDev Arena15671687

Specs and price

Claude Opus 4.7Claude Opus 5
Agent Index54.6 (#29)65.4 (#11)
Agent $/M$2.31$2.31
Input / output $/M$5.00 / $25.00$5.00 / $25.00
Context1M1M
ReleasedApr 16, 2026Jul 24, 2026
WeightsClosedClosed
API hosts56

Don’t pick one. Route.

Shogo can run Claude Opus 4.7 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