SShogo Bench

GPT-6.1 Sol vs Grok 4.7

GPT-6.1 Sol leads Grok 4.7 by 15.2 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-6.1 Sol wins 17 and Grok 4.7 wins 2 of 19 shared benchmarks. GPT-6.1 Sol is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGPT-6.1 SolGrok 4.7
Agentic coding8058
Long-horizon autonomy7869
Knowledge-work agents5447
Computer use6639
Security & context learning6250

Shared benchmarks

BenchmarkGPT-6.1 SolGrok 4.7
APEX-Agentsindex60.0%70.0%
Vending-Bench 2index$12,861$10,537
ARC-AGI98.5%90.2%
ARC-AGI-294.2%61.4%
Chess Puzzles68.0%41.0%
CritPt31.7%18.0%
DTBench96.5%96.0%
FrontierCode50.2%47.6%
FrontierMath Tier 4100.0%17.1%
FrontierMath Tiers 1-393.7%53.0%
GPQA Diamond95.4%92.7%
LMCA62.8%49.4%
MirrorCode61.1%54.4%
OTIS Mock AIME100.0%98.1%
ProofBench99.0%26.0%
SciCode55.8%57.8%
SimpleQA Verified73.9%56.0%
WebDev Arena17591638
WeirdML v338.3%8.5%

Specs and price

GPT-6.1 SolGrok 4.7
Agent Index70 (#5)54.8 (#27)
Agent $/M$0.84$0.98
Input / output $/M$2.00 / $10.00$2.00 / $6.00
Context1.1M500K
ReleasedSep 29, 2026Sep 21, 2026
WeightsClosedClosed
API hosts65

Don’t pick one. Route.

Shogo can run GPT-6.1 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