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-120b | DeepSeek V4 Flash 0731 | |
|---|---|---|
| Provider | OpenAI | DeepSeek |
| Input $/1M | $0.037 | $0.090 |
| Output $/1M | $0.170 | $0.180 |
| Blended $/1M | $0.070 | $0.113 |
| Context window | 131K | 1.0M |
| Max output | 131K | 384K |
| Released | Aug 2025 | Jul 2026 |
| Licence | Open weights | Open 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.