Compare / DeepSeek-V3.1 vs gpt-oss-20b

DeepSeek-V3.1 vs gpt-oss-20b

Which is cheaper, which is more capable, and which does better at each kind of work, from 16 results on 3 sources that measured both models.

DeepSeekDeepSeek-V3.1 Released 21 Aug 2025 · $0.27 in · $1.00 out
OpenAIgpt-oss-20b Released 5 Aug 2025 · $0.030 in · $0.14 out
DeepSeek-V3.1 wins 14gpt-oss-20b wins 2

Of the 16 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee). See also DeepSeek vs OpenAI, every model from both labs.

DeepSeek-V3.1 or gpt-oss-20b? The short answer

Pick DeepSeek-V3.1 if quality matters most: it scores higher (Intelligence Index 13.7 against 10.0). Pick gpt-oss-20b if cost matters more: it costs 7.9 times less per token.

  • gpt-oss-20b is cheaper: $0.058 against $0.45 per million tokens, 7.9 times less.
  • DeepSeek-V3.1 scores higher on the Artificial Analysis Intelligence Index: 13.7 against 10.0.
  • DeepSeek-V3.1 is newer: released 21 Aug 2025, against 5 Aug 2025 for gpt-oss-20b.
  • On third-party benchmarks, on the results both models have: DeepSeek-V3.1 does better for reasoning and knowledge and writing.

Head to head

13.7
Intelligence Index
10.0
$0.45
Price per million tokens, blendedlower is better
$0.058
163,840
Context window, tokens
131,072

Every fact side by side

DeepSeek-V3.1gpt-oss-20b
Price per million tokens$0.27 in · $1.00 out$0.030 in · $0.14 out
Blended (3 in : 1 out)$0.45$0.058
Cheapest host, blended$0.42 (DeepInfra, FP4)$0.022 (PrimeIntellect, FP4)
Intelligence Index13.710.0
Spring Prompt overall––
Output speed, tokens a second–277
Context window163,840 tokens131,072 tokens
Released21 Aug 2025 (newer)5 Aug 2025
WeightsOpenOpen
Developer based inChinathe US

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls not measured 130 of 159
Reasoning and knowledgeHard questions across science, maths and general knowledge 120 of 187 132 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 83 of 169 155 of 169
Sticking to the factsSummarising without inventing things, and factual answers 19 of 139 not measured

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureDeepSeek-V3.1gpt-oss-20b
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 116 · 237 of 387 measured 1,417 1,318
Business, management and finance · TextArena rating, higher is better 112 · 213 of 380 measured 1,417thinking reasoning 1,323
Creative writing · TextArena rating, higher is better 91 · 275 of 385 measured 1,402thinking reasoning 1,240
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 142 · 176 of 249 measured 13.7no reasoning 10.0low reasoning
GPQA Diamond% of questions, higher is better 122 · 159 of 232 measured 77.9%thinking reasoning 68.8%high reasoning
Humanity's Last Exam% of questions, higher is better 138 · 153 of 250 measured 14.3%thinking reasoning 11.0%high reasoning
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 73 · 182 of 230 measured 51.9thinking reasoning 24.6low reasoning
Requested-length error · UGI% off the requested word count, lower is better 166 · 221 of 230 measured 30.0%no reasoning 98.0%low reasoning
Style adherence · UGIscore from 0 to 1, higher is better 66 · 187 of 230 measured 0.36thinking reasoning 0.31medium reasoning
Show all 16 results (7 more)
MeasureDeepSeek-V3.1gpt-oss-20b
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 122 · 220 of 338 measured 1,432thinking reasoning 1,314
Instruction following · TextArena rating, higher is better 97 · 257 of 387 measured 1,416thinking reasoning 1,281
Writing, literature and language · TextArena rating, higher is better 94 · 261 of 386 measured 1,407thinking reasoning 1,275
Artificial Analysis reported by Artificial Analysis · 4 results
IFBench% of instructions, higher is better 127 · 69 of 195 measured 41.5%thinking reasoning 65.1%high reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 149 · 184 of 241 measured 56.7%thinking reasoning 34.7%high reasoning
Terminal-Bench Hard% of tasks, higher is better 78 · 127 of 190 measured 25.0%thinking reasoning 10.6%high reasoning
τ²-bench telecom% of tasks, higher is better 117 · 96 of 193 measured 37.4%thinking reasoning 60.2%high reasoning

Quick answers

Is DeepSeek-V3.1 better than gpt-oss-20b?

Pick DeepSeek-V3.1 if quality matters most: it scores higher (Intelligence Index 13.7 against 10.0). Pick gpt-oss-20b if cost matters more: it costs 7.9 times less per token.

Which is cheaper, DeepSeek-V3.1 or gpt-oss-20b?

gpt-oss-20b is cheaper: $0.058 against $0.45 per million tokens, 7.9 times less.

Which is better for reasoning and knowledge, DeepSeek-V3.1 or gpt-oss-20b?

DeepSeek-V3.1 ranks 120 of 187 models on sale for hard questions across science, maths and general knowledge, against 132 for gpt-oss-20b.

Which is better for writing, DeepSeek-V3.1 or gpt-oss-20b?

DeepSeek-V3.1 ranks 83 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 155 for gpt-oss-20b.

Which has the bigger context window, DeepSeek-V3.1 or gpt-oss-20b?

DeepSeek-V3.1: 163,840 tokens, against 131,072 for gpt-oss-20b.

Run DeepSeek-V3.1 and gpt-oss-20b on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.