← Back to Model Hub/SIDE-BY-SIDE REVIEW
SHARE THIS:

GPT-5 vs gpt-oss-120b

How do these models stack up? Below is an expert side-by-side comparison of specifications, context window capacity, live pricing per million tokens, and standardized benchmark scores for GPT-5 and gpt-oss-120b.

OpenAI

GPT-5

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...

View Full Specs
OpenAI

gpt-oss-120b

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...

View Full Specs

Technical Specifications

SpecificationGPT-5gpt-oss-120b
ProviderOpenAIOpenAI
Context Window400,000 tokens131,072 tokens
Agent Suitability92/100N/A
Time to First Token (TTFT)320 msN/A
Deployment Modelmanaged apimanaged api
Production Stabilitystablestable
API AvailableYesYes
Released Date2025-08-072025-08-05

API Pricing Comparison

Input Price per Million Tokens

GPT-5

$1.25

gpt-oss-120b

$0.03

Output Price per Million Tokens

GPT-5

$10.00

gpt-oss-120b

$0.15

Want to test both models live?

Run side-by-side prompt prompts in our dynamic Sandbox. Check execution speeds, latency metrics, and compute actual costs in real-time.

Benchmark Performance Metrics

Scores show the raw performance percentages verified across key evaluation suites. Higher bars indicate superior accuracy and capability in that domain.

MMLUGeneral knowledge & multi-task understanding
9210.0%vsN/A
GPT-5
gpt-oss-120b
HumanEvalPython coding & logic synthesis
9400.0%vsN/A
GPT-5
gpt-oss-120b
MATHComplex mathematical problem solving
8950.0%vsN/A
GPT-5
gpt-oss-120b
GPQAGraduate-level expert reasoning
7950.0%vsN/A
GPT-5
gpt-oss-120b
HellaSwagCommonsense reasoning and inference
9850.0%vsN/A
GPT-5
gpt-oss-120b
MT-BenchMulti-turn conversation flow quality
950.0%vsN/A
GPT-5
gpt-oss-120b

GPT-5 Quirks & Gotchas

  • Reliable all-rounder — use as default for most production workflows
  • Not recommended for advanced reasoning chains — use o3-mini instead

gpt-oss-120b Quirks & Gotchas

No developer gotchas reported.