Skip to content

gpt-oss-120b

by OpenAIRank #233Score 40.4

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

Performance Overview

Score
40.4
Rank
#233
24h Change
0
7d Change
-63
State
stable
Confidence
high

Signal Scores

SignalNormalizedWeightContributionFreshness
Capabilities
capability
66.720%13.32026-08-08T12:27:57.432Z
Benchmarks
benchmark
45.630%13.72026-08-08T12:27:57.432Z
Pricing
pricing_tier
99.815%15.02026-08-08T12:27:57.432Z
Context Window
context_window
81.210%8.12026-08-08T12:27:57.432Z
Recency
recency
65.915%9.92026-08-08T12:27:57.432Z
Output Capacity
output_capacity
85.010%8.52026-08-08T12:27:57.432Z

Top Drivers

positive
Pricing
$0.17/M output tokens
$0.17
neutral
Benchmarks
positive
Capabilities
Supports reasoning, tools, JSON mode, streaming
4/7
positive
Recency
Released over 1 year ago
1.0y ago

Capabilities

CapabilitySupported
VisionNo
ReasoningYes
JSON ModeYes
StreamingYes
Function CallingYes
Web SearchNo

Pricing

Input / 1M tokens
$0.04
Output / 1M tokens
$0.17
Context Window
131K
Max Output
131K

Related Models

Related

gpt-oss-120b Tracker - Performance History | LM Market Cap