SShogo Bench

Trinity Large Thinking

Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use

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
22
estimated
Long-horizon autonomy
32
estimated
Knowledge-work agents
20
estimated
Computer use
11
estimated
Security & context learning
22
estimated

Price

Input
$0.25/M
Output
$0.80/M
Cache read
$0.060/M
3:1 blend
$0.39/M
Agent-effective
$0.12/M

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

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%predicted 57
Terminal-Bench 2.0est.8%predicted 16
DeepSWEest.6%predicted 14
FrontierSWEest.5%predicted 2
CursorBenchest.4%predicted 21
GSO-Benchest.4%predicted 4
METR Time Horizonsest.10%predicted 56
Vending-Bench 2est.6%predicted 5
PostTrainBenchest.4%predicted 13
APEX-Agentsest.8%predicted 16
GDPvalest.7%predicted 22
Remote Labor Indexest.5%predicted 1
DeepResearch Benchest.5%predicted 43
OSWorld 2.0est.6%predicted 1
OSWorldest.4%predicted 26
Cybenchest.5%predicted 30
CL-benchest.5%predicted 14

Other benchmarks

BenchmarkCategoryScoreSource
CritPtReasoning0.9%source
SciCodeCoding40.6%source
WebDev ArenaCoding1237source