token.app › Compare › gpt-oss-120b vs DeepSeek V4 Flash 0731

gpt-oss-120b vs DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731 leads on 3 of 3 shared benchmarks. gpt-oss-120b is 1.6× cheaper per token on a blended 3:1 basis. DeepSeek V4 Flash 0731 accepts the larger context window (1.0M).

Head to head
Blended price uses a 3:1 input:output mix
gpt-oss-120bDeepSeek V4 Flash 0731
ProviderOpenAIDeepSeek
Input $/1M$0.037$0.090
Output $/1M$0.170$0.180
Blended $/1M$0.070$0.113
Context window131K1.0M
Max output131K384K
ReleasedAug 2025Jul 2026
LicenceOpen weightsOpen weights
GPQA Diamond 75.8% 91.0%
SimpleQA Verified 13.9% 34.7%
OTIS Mock AIME 88.9% 94.4%
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 $0.113 blended
Choose DeepSeek V4 Flash 0731 if…
  • Higher GPQA Diamond (91.0% vs 75.8%)
  • Higher SimpleQA Verified (34.7% vs 13.9%)
  • Higher OTIS Mock AIME (94.4% vs 88.9%)
  • Larger context window (1.0M)
  • Newer model (released Jul 2026)
FAQ
Which is better, gpt-oss-120b or DeepSeek V4 Flash 0731?
Across the 3 benchmarks both models have independently-run scores for, gpt-oss-120b leads on 0 and DeepSeek V4 Flash 0731 leads on 3. Benchmarks are one input — price and context window are on this page too.
Is gpt-oss-120b cheaper than DeepSeek V4 Flash 0731?
gpt-oss-120b is cheaper: $0.070 versus $0.113 per million tokens blended at 3:1 input:output. Input alone: $0.037 vs $0.090. Output alone: $0.170 vs $0.180.
What context windows do gpt-oss-120b and DeepSeek V4 Flash 0731 have?
gpt-oss-120b: 131,072 tokens. DeepSeek V4 Flash 0731: 1,048,576 tokens.
Who makes gpt-oss-120b and DeepSeek V4 Flash 0731?
gpt-oss-120b is made by OpenAI. DeepSeek V4 Flash 0731 is made by DeepSeek.
Related comparisons