SShogo Bench

Gemma 3 27B IT

Largest open Gemma 3 instruction model for multilingual text generation and visual understanding

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
—
estimated
Long-horizon autonomy
—
estimated
Knowledge-work agents
—
estimated
Computer use
—
estimated
Security & context learning
—
estimated

Price

Input
$0.16/M
Output
$0.49/M
Cache read
$0.079/M
3:1 blend
$0.24/M
Agent-effective
$0.11/M

Cheapest host for agents: Nebius at $0.060/M.

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%—
Terminal-Bench 2.0est.8%—
DeepSWEest.6%—
FrontierSWEest.5%—
CursorBenchest.4%—
GSO-Benchest.4%—
METR Time Horizonsest.10%—
Vending-Bench 2est.6%—
PostTrainBenchest.4%—
APEX-Agentsest.8%—
GDPvalest.7%—
Remote Labor Indexest.5%—
DeepResearch Benchest.5%—
OSWorld 2.0est.6%—
OSWorldest.4%—
Cybenchest.5%—
CL-benchest.5%—

API hosts

Live prices and uptime for every host serving Gemma 3 27B IT via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
Nebius$0.10$0.30$0.040$0.06099.8%fp8
NextBit$0.080$0.35$0.040$0.06099.4%fp8
DeepInfra$0.064$0.13—$0.070100.0%fp8
Parasail$0.080$0.45$0.040$0.070100.0%fp8
DeepInfra$0.080$0.16—$0.080100.0%fp8
DeepInfra$0.12$0.24—$0.1399.7%fp8