Compare / GPT-4.1 mini vs gpt-oss-20b

GPT-4.1 mini vs gpt-oss-20b

Which is cheaper, which is more capable, and which does better at each kind of work, from 16 results on 2 sources that measured both models.

OpenAIGPT-4.1 mini Released 14 Apr 2025 · $0.40 in · $1.60 out
OpenAIgpt-oss-20b Released 5 Aug 2025 · $0.030 in · $0.14 out
GPT-4.1 mini wins 8gpt-oss-20b wins 8

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).

GPT-4.1 mini or gpt-oss-20b? The short answer

They score about the same, so pick gpt-oss-20b: it costs 12 times less per token.

  • gpt-oss-20b is cheaper: $0.058 against $0.70 per million tokens, 12 times less.
  • They score about the same on the Artificial Analysis Intelligence Index (10.2 and 10.0).
  • gpt-oss-20b is newer: released 5 Aug 2025, against 14 Apr 2025 for GPT-4.1 mini.
  • On third-party benchmarks, on the results both models have: GPT-4.1 mini does better for writing; gpt-oss-20b for agents and tool use and reasoning and knowledge.

Head to head

10.2
Intelligence Index
10.0
$0.70
Price per million tokens, blendedlower is better
$0.058
1,047,576
Context window, tokens
131,072

Every fact side by side

GPT-4.1 minigpt-oss-20b
Price per million tokens$0.40 in · $1.60 out$0.030 in · $0.14 out
Blended (3 in : 1 out)$0.70$0.058
Cheapest host, blended$0.70 (Azure)$0.022 (PrimeIntellect, FP4)
Intelligence Index10.210.0
Spring Prompt overall––
Output speed, tokens a second–277
Context window1,047,576 tokens131,072 tokens
Released14 Apr 20255 Aug 2025 (newer)
WeightsClosedOpen
Developer based inthe USthe 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 110 of 159 130 of 159
Reasoning and knowledgeHard questions across science, maths and general knowledge 141 of 187 132 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 118 of 169 155 of 169
Sticking to the factsSummarising without inventing things, and factual answers 131 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.

MeasureGPT-4.1 minigpt-oss-20b
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 160 · 237 of 387 measured 1,383 1,318
Business, management and finance · TextArena rating, higher is better 160 · 213 of 380 measured 1,379 1,323
Creative writing · TextArena rating, higher is better 154 · 275 of 385 measured 1,349 1,240
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 175 · 176 of 249 measured 10.2 10.0low reasoning
GPQA Diamond% of questions, higher is better 171 · 159 of 232 measured 66.4% 68.8%high reasoning
Humanity's Last Exam% of questions, higher is better 199 · 153 of 250 measured 5.0% 11.0%high reasoning
Show all 16 results (10 more)
MeasureGPT-4.1 minigpt-oss-20b
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 171 · 220 of 338 measured 1,383 1,314
Instruction following · TextArena rating, higher is better 159 · 257 of 387 measured 1,373 1,281
Writing, literature and language · TextArena rating, higher is better 158 · 261 of 386 measured 1,361 1,275
Artificial Analysis reported by Artificial Analysis · 7 results
Terminal-Bench 2.1% of tasks, higher is better 105 · 97 of 131 measured 10.1% 13.9%high reasoning
τ-bench banking% of tasks, higher is better 102 · 90 of 121 measured 5.4% 7.0%high reasoning
Artificial Analysis Coding Indexindex score, higher is better 102 · 100 of 130 measured 20.2 20.7high reasoning
IFBench% of instructions, higher is better 143 · 69 of 195 measured 38.3% 65.1%high reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 172 · 184 of 241 measured 44.0% 34.7%high reasoning
Terminal-Bench Hard% of tasks, higher is better 135 · 127 of 190 measured 7.6% 10.6%high reasoning
τ²-bench telecom% of tasks, higher is better 102 · 96 of 193 measured 52.9% 60.2%high reasoning

Quick answers

Is GPT-4.1 mini better than gpt-oss-20b?

They score about the same, so pick gpt-oss-20b: it costs 12 times less per token.

Which is cheaper, GPT-4.1 mini or gpt-oss-20b?

gpt-oss-20b is cheaper: $0.058 against $0.70 per million tokens, 12 times less.

Which is better for agents and tool use, GPT-4.1 mini or gpt-oss-20b?

GPT-4.1 mini ranks 110 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 130 for gpt-oss-20b.

Which is better for reasoning and knowledge, GPT-4.1 mini or gpt-oss-20b?

gpt-oss-20b ranks 132 of 187 models on sale for hard questions across science, maths and general knowledge, against 141 for GPT-4.1 mini.

Which is better for writing, GPT-4.1 mini or gpt-oss-20b?

GPT-4.1 mini ranks 118 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, GPT-4.1 mini or gpt-oss-20b?

GPT-4.1 mini: 1,047,576 tokens, against 131,072 for gpt-oss-20b.

Run GPT-4.1 mini 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.