SShogo Bench

GPT-6 Sol vs Grok 4.7

GPT-6 Sol leads Grok 4.7 by 8.8 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-6 Sol wins 16 and Grok 4.7 wins 3 of 19 shared benchmarks. GPT-6 Sol is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGPT-6 SolGrok 4.7
Agentic coding7258
Long-horizon autonomy7669
Knowledge-work agents4847
Computer use5439
Security & context learning5950

Shared benchmarks

BenchmarkGPT-6 SolGrok 4.7
APEX-Agentsindex54.3%70.0%
Vending-Bench 2index$14,428$10,537
ARC-AGI95.5%90.2%
ARC-AGI-289.6%61.4%
Chess Puzzles56.0%41.0%
CritPt30.9%18.0%
DTBench97.3%96.0%
FrontierCode49.3%47.6%
FrontierMath Tier 490.0%17.1%
FrontierMath Tiers 1-389.8%53.0%
GPQA Diamond94.3%92.7%
LMCA59.1%49.4%
MirrorCode48.9%54.4%
OTIS Mock AIME100.0%98.1%
ProofBench83.0%26.0%
SciCode57.6%57.8%
SimpleQA Verified60.7%56.0%
WebDev Arena16891638
WeirdML v319.7%8.5%

Specs and price

GPT-6 SolGrok 4.7
Agent Index63.6 (#13)54.8 (#27)
Agent $/M$0.92$0.98
Input / output $/M$2.00 / $10.00$2.00 / $6.00
Context1.1M500K
ReleasedSep 22, 2026Sep 21, 2026
WeightsClosedClosed
API hosts55

Don’t pick one. Route.

Shogo can run GPT-6 Sol and Grok 4.7 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo