Noometry

Model comparison

gpt-oss-120b vs Grok 4

Grok 4 is the stronger model overall, scoring 48.1 to 36.3 on the Noometry Index.

Last verified . 35 shared benchmarks.

gpt-oss-120b OpenAI

36.3

Rank #217 Confirmed

Grok 4 xAI

48.1

Rank #56 Confirmed

Summary

  • They share 35 benchmarks with published results for both. gpt-oss-120b scores higher in 1 category and Grok 4 in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Grok 4 leads 63.1 to 31.4.
  • The biggest single-benchmark swing is Fiction.LiveBench: 44.4% for gpt-oss-120b and 94.4% for Grok 4.
  • gpt-oss-120b has downloadable open weights; the other is API-only.

Side by side

gpt-oss-120bGrok 4
ProviderOpenAIxAI
Noometry Index36.348.1
Released2025-08-052025-07-09
WeightsOpenProprietary
Context window131K—
Max output41K—
Input $ / M tokens$0.037—
Output $ / M tokens$0.17—
Results tracked4848

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Grok 4 leads

gpt-oss-120b: 33.5 (#256), Grok 4: 50.3 (#46)

Benchmarkgpt-oss-120bGrok 4
Aider Polyglot41.8%79.6%
WeirdML48.2%45.7%
LMArena Coding13801408
SWE-bench Verified (bash only)26%—
SciCode36%—
ALE-Bench575.62—
AlgoTune1.41—

Agentic & Tool Use Grok 4 leads

gpt-oss-120b: 12.2 (#153), Grok 4: 32.3 (#68)

Benchmarkgpt-oss-120bGrok 4
Terminal-Bench18.7%27.2%
METR Time Horizons56.6%66.6%
APEX-Agents4.4%—
Berkeley Function Calling Leaderboard—63%
GDPval—21.1%
Cybench—43%
DeepResearch Bench—47.3%
BALROG—43.6%
LMArena Search—1142
Vending-Bench 2-21.53—

Reasoning Grok 4 leads

gpt-oss-120b: 20.0 (#245), Grok 4: 36.7 (#65)

Benchmarkgpt-oss-120bGrok 4
SimpleBench22.1%60.5%
Kagi LLM Benchmark58.6%73.6%
Chess Puzzles20%28%
LMArena Hard Prompts13641409
Epoch Capabilities Index139.93146.44
ARC-AGI-2—16%
ARC-AGI-1—66.7%
CritPt1.1%—
Mystery Game Puzzles2%—
DTBench76.3%—
LMCA22.1%—
Surface Evolver Bench25%—
ForecastBench—60.9

Math gpt-oss-120b leads

gpt-oss-120b: 52.5 (#50), Grok 4: 48.4 (#64)

Benchmarkgpt-oss-120bGrok 4
OTIS Mock AIME 2024-202588.9%84%
Omni-MATH68.8%60.3%
LMArena Math13891422
FrontierMath (Feb 2025 set)—19.7%
FrontierMath Tier 4 (v1)—2.1%

Knowledge Grok 4 leads

gpt-oss-120b: 42.4 (#96), Grok 4: 53.8 (#55)

Benchmarkgpt-oss-120bGrok 4
GPQA Diamond75.8%87%
MMLU-Pro79.5%85.1%
Confabulations15.7%12.4%
GPQA (HELM)68.4%72.7%
LMArena Expert13561415
Vectara Hallucination Rate14.2%—

Multimodal Not comparable

gpt-oss-120b: —, Grok 4: 33.7 (#94)

Benchmarkgpt-oss-120bGrok 4
LMArena Vision—1210
GeoBench—45%

Multilingual Grok 4 leads

gpt-oss-120b: 48.0 (#147), Grok 4: 51.8 (#103)

Benchmarkgpt-oss-120bGrok 4
LMArena Non-English13511403
LMArena Chinese13851427
LMArena French13691418
LMArena German13531429
LMArena Japanese13311394
LMArena Korean12821377
LMArena Russian13431410
LMArena Spanish13891420

Instruction Following Grok 4 leads

gpt-oss-120b: 69.3 (#173), Grok 4: 79.2 (#5)

Benchmarkgpt-oss-120bGrok 4
IFEval83.6%94.9%
LMArena Instruction Following13181387

Long Context Grok 4 leads

gpt-oss-120b: 31.4 (#278), Grok 4: 63.1 (#4)

Benchmarkgpt-oss-120bGrok 4
Fiction.LiveBench44.4%94.4%
LMArena Longer Query13191409

Writing & Preference Grok 4 leads

gpt-oss-120b: 46.5 (#217), Grok 4: 58.5 (#116)

Benchmarkgpt-oss-120bGrok 4
LMArena Text13651411
LMArena Creative Writing12751397
Short-Story Creative Writing77.1%76.9%
WildBench84.5%79.7%
LMArena Multi-Turn13401416
EQ-Bench Creative Writing961—

Frequently asked questions

Is gpt-oss-120b better than Grok 4?

Grok 4 is the stronger model overall, scoring 48.1 to 36.3 on the Noometry Index.

Is gpt-oss-120b or Grok 4 better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 33.5 in the Noometry coding category.

How many benchmarks do gpt-oss-120b and Grok 4 share?

35 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Grok 4 has 48.

Related comparisons

Go deeper