Skip to content

gpt-oss-120b

by OpenAIRank #209Score 61.6

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
61.6
Rank
#209
24h Change
+1
7d Change
-10
State
stable
Confidence
high

Signal Scores

SignalNormalizedWeightContributionFreshness
Capabilities
capability
66.720%13.32026-09-22T14:23:55.758Z
Benchmarks
benchmark
60.330%18.12026-09-22T14:23:55.758Z
Pricing
pricing_tier
99.415%14.92026-09-22T14:23:55.758Z
Context Window
context_window
81.210%8.12026-09-22T14:23:55.758Z
Recency
recency
57.715%8.62026-09-22T14:23:55.758Z
Output Capacity
output_capacity
77.010%7.72026-09-22T14:23:55.758Z

Top Drivers

positive
Benchmarks
positive
Pricing
$0.60/M output tokens
$0.60
positive
Capabilities
Supports reasoning, tools, JSON mode, streaming
4/7
neutral
Recency
Released over 1 year ago
1.1y ago

Capabilities

CapabilitySupported
VisionNo
ReasoningYes
JSON ModeYes
StreamingYes
Function CallingYes
Web SearchNo

Pricing

Input / 1M tokens
$0.15
Output / 1M tokens
$0.60
Context Window
131K
Max Output
66K

Related Models

Related

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