SYSTEM ONE MODEL INTELLIGENCE DIRECTORY|Decisions, Not Strings ∵ ⩆
Status: ONLINE
Last updated:
ARCHITECTURAL OVERVIEW

Performance, Latency & Economic Benchmarks

Comprehensive comparison of System One decision models against traditional autoregressive frontier LLMs across real-world workloads, automated evaluations, and cost metrics.

SYSTEM_ONE_VS_FRONTIER_LLMS // COMPREHENSIVE_EVAL
ALL_TIERS
Model / PipelineInput / MTokOutput / MTokP50 LatencySampling MethodType Error RateCost / 100k Decisions
TypeSafe Jev 1.1$0.042 ($42/BT)$0.00 (FREE)114msParallel decision0.0% (Guaranteed)$0.008
OpenAI GPT-4o$2.50$10.003,450msAutoregressive1.2%$1.250
Claude 3.5 Sonnet$3.00$15.003,200msAutoregressive0.9%$2.400
DeepSeek V3$0.14$0.281,950msAutoregressive1.5%$0.080
Google Gemini 1.5 Flash$0.075$0.301,400msAutoregressive2.1%$0.045
Architecture 01: Decision Gating

System One Evaluation Pipeline

Jev evaluates structured decisions in parallel without autoregressive token generation, enabling dramatic cost reductions for high-volume pass/fail assertions compared to invoking frontier LLMs.

Benchmarks Pending Verification
Architecture 02: Bulk Triage

High-Throughput Content Classification

The dual-system architecture processes bulk content categorization workloads by delegating filtering and classification to Jev, reserving frontier LLMs for high-value synthesis on qualified candidates only.

Benchmarks Pending Verification
Architecture 03: Agent Routing

Dual-System Agent Architecture

Autonomous agents using a dual-system approach delegate high-frequency state evaluation decisions to Jev while retaining frontier LLMs for strategic planning and complex reasoning tasks.

Benchmarks Pending Verification

Verified Benchmark Sources

D
Diogo Almeida (TypeSafe AI)@typesafeai
Sep 15, 2026
Official
"Jev is the first frontier model built for automation rather than chat. Input tokens are priced at $0.042 per million tokens ($42 per billion). Output tokens are free because decisions are sampled in parallel."

Context: Official launch paper and system announcement for the first System One Model.