gpt-oss-120bvsGrok 4.6

gpt-oss-120b
Grok 4.6
Specifications
Parameters
117B
Context window
128k
Benchmarks
Nonsense detection
BullshitBench v2
11%
Coding
SWE-Bench Verified
62.4%
Agentic coding
CursorBench v3.2
69.9%
Agentic coding
DeepSWE 1.1
65.9%
Agentic coding
FrontierCode v1.1 (Extended) · extended split
61.3%
Expert software engineering
APEX-SWE
56.4%
Agentic terminal coding
Terminal-Bench 3.0
26%
Expert agentic work
APEX-Agents
57.5%
Multidisciplinary reasoning
Humanity's Last Exam · no tools
14.9%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
19%
Science
GPQA Diamond
80.1%
General knowledge
MMLU
90%
Agentic legal work
Harvey's Legal Agent Benchmark
15.8%
Overall intelligence
AA Intelligence Index
61
Knowledge work
GDPval-AA v2
1753
Knowledge work
AA-Briefcase
1577
Overview
CompanyOpenAISpaceXAI
Release dateAug 5 2025Aug 12 2026
AccessOpen WeightProprietary

Which is better: gpt-oss-120b or Grok 4.6?

gpt-oss-120b and Grok 4.6 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. gpt-oss-120b shipped 372 days before Grok 4.6, so benchmark comparisons should account for the intervening progress.

gpt-oss-120b is open weight, while Grok 4.6 is proprietary.

Direct benchmark comparisons are unavailable — gpt-oss-120b and Grok 4.6 don't publish scores on any of the same benchmarks.

Frequently asked questions

gpt-oss-120b was released by OpenAI on Aug 5 2025.

Grok 4.6 was released by SpaceXAI on Aug 12 2026.

gpt-oss-120b is an open weight model released by OpenAI. Grok 4.6 is a proprietary model released by SpaceXAI.

Other comparisons