SShogo Bench

Nemotron 3.5 Super VL

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video…

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
$0.15/M
Output
$0.50/M
Cache read
$0.020/M
3:1 blend
$0.24/M
Agent-effective
$0.060/M

Cheapest host for agents: Darkbloom at $0.030/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 Nemotron 3.5 Super VL via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
Darkbloom$0.060$0.35$0.010$0.03093.8%nvfp4
CoreWeave$0.15$0.47$0.020$0.060100.0%nvfp4
DeepInfra$0.15$0.50$0.020$0.06099.6%fp4
PrimeIntellect$0.15$0.50$0.020$0.06097.6%nvfp4
Together$0.15$0.50$0.020$0.06087.8%—
BaseTen$0.20$0.50$0.040$0.08099.9%fp4
Venice$0.20$0.50$0.040$0.08099.8%fp4
Crusoe$0.10$0.40$0.080$0.1099.4%bf16
Nebius$0.30$0.90$0.060$0.13100.0%fp4
PrimaLabs$0.25$1.50$0.050$0.1594.0%nvfp4
Io Net$0.75$2.30$0.17$0.3569.8%nvfp4