SShogo Bench

Llama 3.2 1B Instruct

Open Llama instruction model for multilingual chat, reasoning, and coding

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
2
estimated
Long-horizon autonomy
6
estimated
Knowledge-work agents
6
estimated
Computer use
0
estimated
Security & context learning
2
estimated

Price

Input
$0.027/M
Output
$0.20/M
Cache read
—/M
3:1 blend
$0.070/M
Agent-effective
$0.040/M

Cheapest host for agents: Cloudflare 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 9
Terminal-Bench 2.0est.8%predicted 0
DeepSWEest.6%predicted 0
FrontierSWEest.5%predicted 0
CursorBenchest.4%predicted 3
GSO-Benchest.4%predicted 0
METR Time Horizonsest.10%predicted 11
Vending-Bench 2est.6%predicted 0
PostTrainBenchest.4%predicted 2
APEX-Agentsest.8%predicted 0
GDPvalest.7%predicted 1
Remote Labor Indexest.5%predicted 0
DeepResearch Benchest.5%predicted 29
OSWorld 2.0est.6%predicted 0
OSWorldest.4%predicted 0
Cybenchest.5%predicted 0
CL-benchest.5%predicted 4

Other benchmarks

BenchmarkCategoryScoreSource
BALROGLong-horizon6.6%source
GPQA DiamondReasoning23.9%source
OTIS Mock AIMEMath0.6%source

API hosts

Live prices and uptime for every host serving Llama 3.2 1B Instruct via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
Cloudflare$0.027$0.20—$0.04094.7%—