0

gpt-oss-120b vs Kimi K2.5

Head to head on 19 shared benchmarks, with price, context window, and release dates.

Benchmark scores

49

evals · sort by any column, ⤢ to expand fullscreen

Model
Kimi K2.5

Moonshot AI

68.3%39.0%1576elo74.978.9%13.2%43.7%72.5%77.9%61.4%57.4%77.7%84.9%76.0%39.6%70.8%74.2%18.9%81.3%--96.1--35.8%27.9%-95.478.5%10421---62.0%39.3%76.4%-87.1-66.5%63.3%49.9%-7367.3%-69.426.3%17.5%56.8%
gpt-oss-120b

OpenAI

58.2%13.0%959elo35.867.2%5.9%58.3%51.0%60.2%38.8%50.3%48.6%68.9%39.2%36.0%26.0%71.6%5.3%45.0%41.8%66.7%-38.9%7.6%--57.6---70.7%1.621.53---80.0%-77.5%---97.9%--65.6%---49.6%
2 / 2 models
Attributegpt-oss-120b

OpenAI

Kimi K2.5

Moonshot AI

DescriptionGPT-Oss 120b is an AI model from OpenAI, released with open weights.Kimi K2.5 is an AI model from Kimi.
FamilyGPTKimi
Params--
Open weightsopenclosed
Licenseapache-2.0Modified MIT
Released5 Aug 202527 Jan 2026
Context131,072262,144
Input $/1M$0.15$0.60
Output $/1M$0.60$3.00
Cache read $/1M$0.030$0.100
Cache write $/1M--
Speed186 tok/s0 tok/s
Latency0.50 s0.00 s
Modalitiestexttext, image
Providers--
PublisherOpenAIMoonshot AI
Reported scores
GPQA Diamond67.2% (AA)
LiveCodeBench70.7% (AA)
MMLU-Pro77.5% (AA)
SciCode36.0% (AA)

FAQ

Is gpt-oss-120b or Kimi K2.5 better?
Across the 19 benchmarks both models report on Sophon, Kimi K2.5 leads on 18 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
How do gpt-oss-120b and Kimi K2.5 compare on GPQA Diamond?
gpt-oss-120b scores 67.2% and Kimi K2.5 scores 78.9% on GPQA Diamond.
Which is cheaper, gpt-oss-120b or Kimi K2.5?
gpt-oss-120b is cheaper at $0.60 per million output tokens against $3.00 for Kimi K2.5 - about 5.0x.
When were gpt-oss-120b and Kimi K2.5 released?
gpt-oss-120b was released 5 Aug 2025 by OpenAI. Kimi K2.5 was released 27 Jan 2026 by Moonshot AI.

Comparing something else? Build your own side-by-side.