SShogo Bench

Claude Sonnet 5.5 vs GPT-6.1 Sol

GPT-6.1 Sol leads Claude Sonnet 5.5 by 1.0 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Sonnet 5.5 wins 9 and GPT-6.1 Sol wins 10 of 20 shared benchmarks. Claude Sonnet 5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Sonnet 5.5GPT-6.1 Sol
Agentic coding7980
Long-horizon autonomy7578
Knowledge-work agents5754
Computer use6166
Security & context learning6162

Shared benchmarks

BenchmarkClaude Sonnet 5.5GPT-6.1 Sol
APEX-Agentsindex75.5%60.0%
Vending-Bench 2index$11,165$12,861
ARC-AGI96.5%98.5%
ARC-AGI-283.9%94.2%
Chess Puzzles59.0%68.0%
CritPt31.4%31.7%
DTBench97.3%96.5%
FrontierCode52.1%50.2%
FrontierMath Tier 480.5%100.0%
FrontierMath Tiers 1-388.8%93.7%
GPQA Diamond95.6%95.4%
LMCA68.3%62.8%
MirrorCode97.8%61.1%
OTIS Mock AIME100.0%100.0%
ProofBench100.0%99.0%
SciCode61.0%55.8%
SimpleBench75.9%82.9%
SimpleQA Verified46.5%73.9%
WebDev Arena17861759
WeirdML v319.9%38.3%

Specs and price

Claude Sonnet 5.5GPT-6.1 Sol
Agent Index69 (#9)70 (#5)
Agent $/M$0.84$0.84
Input / output $/M$2.00 / $10.00$2.00 / $10.00
Context1M1.1M
ReleasedSep 28, 2026Sep 29, 2026
WeightsClosedClosed
API hosts56

Don’t pick one. Route.

Shogo can run Claude Sonnet 5.5 and GPT-6.1 Sol side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo