token.app › Compare › gpt-oss-120b vs GLM 5.2

gpt-oss-120b vs GLM 5.2

GLM 5.2 leads on 2 of 3 shared benchmarks. gpt-oss-120b is 5.5× cheaper per token on a blended 3:1 basis. GLM 5.2 accepts the larger context window (1.0M).

Head to head
Blended price uses a 3:1 input:output mix
gpt-oss-120bGLM 5.2
ProviderOpenAIZhipu AI
Input $/1M$0.037$0.252
Output $/1M$0.170$0.792
Blended $/1M$0.070$0.387
Context window131K1.0M
Max output131K128K
ReleasedAug 2025Jun 2026
LicenceOpen weightsOpen weights
GPQA Diamond 75.8% 91.9%
SimpleQA Verified 13.9% 38.1%
OTIS Mock AIME 88.9% 86.4%
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose gpt-oss-120b if…
  • Costs less per token — $0.070 vs $0.387 blended
  • Higher OTIS Mock AIME (88.9% vs 86.4%)
Choose GLM 5.2 if…
  • Higher GPQA Diamond (91.9% vs 75.8%)
  • Higher SimpleQA Verified (38.1% vs 13.9%)
  • Larger context window (1.0M)
  • Newer model (released Jun 2026)
FAQ
Which is better, gpt-oss-120b or GLM 5.2?
Across the 3 benchmarks both models have independently-run scores for, gpt-oss-120b leads on 1 and GLM 5.2 leads on 2. Benchmarks are one input — price and context window are on this page too.
Is gpt-oss-120b cheaper than GLM 5.2?
gpt-oss-120b is cheaper: $0.070 versus $0.387 per million tokens blended at 3:1 input:output. Input alone: $0.037 vs $0.252. Output alone: $0.170 vs $0.792.
What context windows do gpt-oss-120b and GLM 5.2 have?
gpt-oss-120b: 131,072 tokens. GLM 5.2: 1,048,576 tokens.
Who makes gpt-oss-120b and GLM 5.2?
gpt-oss-120b is made by OpenAI. GLM 5.2 is made by Zhipu AI.
Related comparisons