SShogo Bench

GLM-5

General GLM flagship for coding, analysis, and tool-heavy engineering workflows

Shogo Agent Index

Supported#62 of 92
36.5range 27.7–45.4 · 27% of weight measured
Agentic coding
38
46% measured
Long-horizon autonomy
54
30% measured
Knowledge-work agents
27
estimated
Computer use
21
estimated
Security & context learning
35
50% measured

Price

Input
$0.60/M
Output
$2.69/M
Cache read
$0.15/M
3:1 blend
$1.12/M
Agent-effective
$0.33/M

Cheapest host for agents: GMICloud at $0.27/M.

Agent-effective = 20 input tokens per output token, 85% cache hits. Why.

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verified72.1%8%source
Terminal-Bench 2.052.4%8%Terminus 2
DeepSWEest.6%predicted 27
FrontierSWEest.5%predicted 5
CursorBenchest.4%predicted 28
GSO-Benchest.4%predicted 10
METR Time Horizonsest.10%predicted 66
Vending-Bench 2$4,4326%source
PostTrainBenchest.4%predicted 18
APEX-Agentsest.8%predicted 27
GDPvalest.7%predicted 32
Remote Labor Indexest.5%predicted 1
DeepResearch Benchest.5%predicted 45
OSWorld 2.0est.6%predicted 3
OSWorldest.4%predicted 49
Cybenchest.5%predicted 51
CL-bench18.7%5%source

Other benchmarks

BenchmarkCategoryScoreSource
ARC-AGIReasoning44.7%source
ARC-AGI-2Reasoning4.9%source
GPQA DiamondReasoning87.8%source
OTIS Mock AIMEMath80.0%source
SimpleBenchReasoning53.2%source
WebDev ArenaCoding1436source

API hosts

Live prices and uptime for every host serving GLM-5 via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
GMICloud$0.60$1.92$0.12$0.2799.1%fp8
StreamLake$0.60$1.92$0.12$0.2799.9%fp8
Baidu$0.70$2.24$0.14$0.32100.0%fp8
SiliconFlow$0.95$2.55$0.20$0.4299.4%fp8
Novita$1.00$3.20$0.20$0.46100.0%fp8
Venice$1.00$3.20$0.20$0.4698.4%fp8
Z.AI$1.00$3.20$0.20$0.4699.9%fp8
Venice$1.20$4.00$0.24$0.56100.0%—
Amazon Bedrock$1.00$3.20—$1.1099.9%—