SShogo Bench

Claude Opus 5 vs GPT-6 Sol

Claude Opus 5 leads GPT-6 Sol by 1.8 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Opus 5 wins 9 and GPT-6 Sol wins 11 of 20 shared benchmarks. GPT-6 Sol is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 5GPT-6 Sol
Agentic coding7472
Long-horizon autonomy7476
Knowledge-work agents5248
Computer use5654
Security & context learning5959

Shared benchmarks

BenchmarkClaude Opus 5GPT-6 Sol
APEX-Agentsindex65.8%54.3%
Vending-Bench 2index$11,182$14,428
ARC-AGI97.5%95.5%
ARC-AGI-290.4%89.6%
Chess Puzzles43.0%56.0%
CritPt29.1%30.9%
DTBench97.9%97.3%
FrontierCode53.4%49.3%
FrontierMath Tier 473.2%90.0%
FrontierMath Tiers 1-385.6%89.8%
GPQA Diamond93.9%94.3%
LMCA64.5%59.1%
MirrorCode87.8%48.9%
OTIS Mock AIME98.9%100.0%
ProofBench99.0%83.0%
SciCode56.4%57.6%
SimpleBench80.6%73.1%
SimpleQA Verified59.9%60.7%
WebDev Arena16871689
WeirdML v319.0%19.7%

Specs and price

Claude Opus 5GPT-6 Sol
Agent Index65.4 (#11)63.6 (#13)
Agent $/M$2.31$0.92
Input / output $/M$5.00 / $25.00$2.00 / $10.00
Context1M1.1M
ReleasedJul 24, 2026Sep 22, 2026
WeightsClosedClosed
API hosts65

Don’t pick one. Route.

Shogo can run Claude Opus 5 and GPT-6 Sol side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo