SShogo Bench

Gemma 4 31B IT

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

Shogo Agent Index

Unranked

Not ranked yet: 0 agentic benchmarks measured, and we need at least 2 plus an overall capability score. It will be ranked as results are published.

Agentic coding
29
estimated
Long-horizon autonomy
38
estimated
Knowledge-work agents
24
estimated
Computer use
18
estimated
Security & context learning
30
estimated

Price

Input
Free/M
Output
Free/M
Cache read
—/M
3:1 blend
Free/M
Agent-effective
Free/M

Cheapest host for agents: Chutes at $0.040/M.

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 64
Terminal-Bench 2.0est.8%predicted 30
DeepSWEest.6%predicted 22
FrontierSWEest.5%predicted 3
CursorBenchest.4%predicted 25
GSO-Benchest.4%predicted 7
METR Time Horizonsest.10%predicted 63
Vending-Bench 2est.6%predicted 11
PostTrainBenchest.4%predicted 16
APEX-Agentsest.8%predicted 22
GDPvalest.7%predicted 28
Remote Labor Indexest.5%predicted 1
DeepResearch Benchest.5%predicted 44
OSWorld 2.0est.6%predicted 2
OSWorldest.4%predicted 41
Cybenchest.5%predicted 44
CL-benchest.5%predicted 16

Other benchmarks

BenchmarkCategoryScoreSource
CritPtReasoning1.4%source
DTBenchKnowledge82.7%source
GPQA DiamondReasoning75.8%source
LMCAKnowledge39.3%source
OTIS Mock AIMEMath73.3%source
SciCodeCoding45.5%source
SimpleQA VerifiedKnowledge10.4%source
WebDev ArenaCoding1364source

API hosts

Live prices and uptime for every host serving Gemma 4 31B IT via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
Chutes$0.12$0.37$0.012$0.04099.9%fp4
NextBit$0.13$0.34$0.075$0.09099.9%fp4
Parasail$0.15$0.40$0.060$0.09099.2%fp8
DeepInfra$0.14$0.51$0.075$0.10100.0%fp4
PrimeIntellect$0.15$0.25$0.076$0.1098.5%fp8
CoreWeave$0.10$0.34$0.10$0.11100.0%fp4
KT$0.10$0.34$0.10$0.11100.0%—
Venice$0.12$0.36$0.090$0.11100.0%fp4
Modal$0.34$0.10$0.10$0.13100.0%—
Crusoe$0.14$0.40$0.14$0.15100.0%bf16
Friendli$0.14$0.40—$0.15100.0%—
Novita$0.14$0.40—$0.1599.8%bf16
DeepInfra$0.16$0.32—$0.1798.9%fp8
DeepInfra$0.20$0.40—$0.21100.0%fp8
DeepInfra$0.30$0.60—$0.3199.3%fp8
ModelRun$0.75$1.00$0.20$0.32100.0%fp4
SiliconFlow$0.75$1.00$0.25$0.36100.0%fp8
SambaNova$0.38$1.15—$0.4293.6%—