SShogo Bench

GLM-5.3 vs GPT-6.1 Terra

GPT-6.1 Terra leads GLM-5.3 by 13.8 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GLM-5.3 wins 1 and GPT-6.1 Terra wins 9 of 10 shared benchmarks. GPT-6.1 Terra is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGLM-5.3GPT-6.1 Terra
Agentic coding6279
Long-horizon autonomy6874
Knowledge-work agents4356
Computer use4063
Security & context learning5162

Shared benchmarks

BenchmarkGLM-5.3GPT-6.1 Terra
APEX-Agentsindex56.6%68.3%
Vending-Bench 2index$8,164$9,107
CritPt19.1%28.0%
FrontierMath Tier 429.3%92.7%
FrontierMath Tiers 1-368.8%90.9%
GPQA Diamond90.9%94.3%
OTIS Mock AIME91.1%100.0%
SciCode59.0%55.1%
SimpleBench66.2%72.2%
SimpleQA Verified41.0%57.3%

Specs and price

GLM-5.3GPT-6.1 Terra
Agent Index55.2 (#25)69 (#8)
Agent $/M$0.61$0.42
Input / output $/M$1.20 / $4.18$1.00 / $5.00
Context1M1.1M
ReleasedAug 14, 2026Oct 26, 2026
WeightsOpenClosed
API hosts494

Don’t pick one. Route.

Shogo can run GLM-5.3 and GPT-6.1 Terra side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo