Is gpt-oss-120b better than Llama 4 Maverick?

On accuracy they are statistically tied: gpt-oss-120b scored 58.8% and Llama 4 Maverick 59.0% on the same 80 questions from open datasets. Similar accuracy; gpt-oss-120b costs less per question.

Which is cheaper, gpt-oss-120b or Llama 4 Maverick?

gpt-oss-120b is cheaper: $0.00013 per question as billed, against $0.00059. List prices: gpt-oss-120b $0.15 in / $0.6 out, Llama 4 Maverick $0.1875 in / $0.6525 out per million tokens.

Which is faster, gpt-oss-120b or Llama 4 Maverick?

gpt-oss-120b is faster at 82 output tokens per second, against 13. Time to first token: 0.5 s for gpt-oss-120b, 0.7 s for Llama 4 Maverick.

Which has the larger context window, gpt-oss-120b or Llama 4 Maverick?

Llama 4 Maverick, with 524k tokens against 131k.

Head to head · tested 27 Oct 2026

gpt-oss-120b vs Llama 4 Maverick: accuracy, speed and price

Similar accuracy; gpt-oss-120b costs less per question.

OpenAIgpt-oss-120b58.8% score · #41$0.00013 per question82 tok/s

MetaLlama 4 Maverick59.0% score · #40$0.00059 per question13 tok/s

Verdict

Built from the measurements below

Accuracy is too close to call: gpt-oss-120b scored 58.8% and Llama 4 Maverick 59.0% on the same 80 questions, a gap within what chance alone could produce.
gpt-oss-120b is 4.7× cheaper per question as billed ($0.00013 vs $0.00059), reasoning tokens included.
gpt-oss-120b generates text 6.1× faster: 82 tokens per second against 13.
gpt-oss-120b starts answering sooner: 0.5 s to the first token, against 0.7 s for Llama 4 Maverick.
Llama 4 Maverick accepts more context: 524k tokens against 131k.

Which should you choose?

Choose gpt-oss-120b for the lower cost per correct answer ($0.00021 against $0.001), faster streaming, a quicker first token and more hosts to choose from on OpenRouter (23 against 3). Choose Llama 4 Maverick for a 524k-token context window. The widest subject gap is in law: Llama 4 Maverick answered 3 of 6 correctly, gpt-oss-120b 1 of 6. With so few questions per subject, treat this as a lead to test on your own prompts, not a result.

Accuracy gap -0.2 points (z = -0.03). A winner is called only when z is at least 1.96, the usual 95% threshold. Speed, latency and price need a 10% margin.

Head to head

Same questions, same prompt, same API

Measure	gpt-oss-120b	Llama 4 Maverick	Edge
Verification scoreHigher is better	58.8%	59.0%	Too close to call
Cost per questionLower is better	$0.00013	$0.00059	gpt-oss-120b
Output speedHigher is better	82	13	gpt-oss-120b
Time to first tokenLower is better	0.5 s	0.7 s	gpt-oss-120b
End-to-end response timeLower is better	5.4 s	27.9 s	gpt-oss-120b
Tokens per questionLower is better	546	784	gpt-oss-120b
Context windowHigher is better	131k	524k	Llama 4 Maverick

Side by side

Bars are scaled to the larger of the two values. The winner on each measure is marked in bold.

Every measure

gpt-oss-120b first, Llama 4 Maverick second

Verification scorehigher is better

gpt-oss-120b58.8%

Llama 4 Maverick59.0%

Cost per questionlower is better

gpt-oss-120b$0.00013

Llama 4 Maverick$0.00059

Output speedhigher is better

gpt-oss-120b82

Llama 4 Maverick13

Time to first tokenlower is better

gpt-oss-120b0.5 s

Llama 4 Maverick0.7 s

End-to-end response timelower is better

gpt-oss-120b5.4 s

Llama 4 Maverick27.9 s

Tokens per questionlower is better

gpt-oss-120b546

Llama 4 Maverick784

Context windowhigher is better

gpt-oss-120b131k

Llama 4 Maverick524k

Score vs. cost per question

Both models in color, every other model in grey

Results by subject and dataset

Questions answered correctly. Small samples: a gap of one or two questions is noise.

Subject	Questions	gpt-oss-120b	Llama 4 Maverick
Science	30	23/30	18/30
Engineering	15	6/15	6/14
Medicine	11	4/11	5/10
Economics	9	7/9	7/9
Law	6	1/6	3/6
Humanities & social science	9	6/9	7/9
SuperGPQA dataset	50	25/50	23/49
MMLU-Pro dataset	30	22/30	23/29

Specifications and pricing

From OpenRouter's catalogue, plus the leaderboard's test dates

Specification	gpt-oss-120b	Llama 4 Maverick
Creator	OpenAI	Meta
Released	5 Aug 2025	5 Apr 2025
Weights	Open weights	Open weights
Reasoning	Yes	No
Input	text	text, image
Output	text	text
Context window	131k tokens	524k tokens
Knowledge cutoff	30 Jun 2024	31 Aug 2024
List price in / out per 1M	$0.15 / $0.6	$0.1875 / $0.6525
Blended price per 1M (3:1)	$0.26	$0.30
Cheapest host	Near AI · $0.03 / $0.15	DigitalOcean · $0.1875 / $0.6525
Hosts on OpenRouter	23	3
Last tested	25 Oct 2026	25 Oct 2026

Compare any two models →

gpt-oss-120b vs Llama 4 Maverick: frequently asked questions

Is gpt-oss-120b better than Llama 4 Maverick?: On accuracy they are statistically tied: gpt-oss-120b scored 58.8% and Llama 4 Maverick 59.0% on the same 80 questions from open datasets. Similar accuracy; gpt-oss-120b costs less per question.
Which is cheaper, gpt-oss-120b or Llama 4 Maverick?: gpt-oss-120b is cheaper: $0.00013 per question as billed, against $0.00059. List prices: gpt-oss-120b $0.15 in / $0.6 out, Llama 4 Maverick $0.1875 in / $0.6525 out per million tokens.
Which is faster, gpt-oss-120b or Llama 4 Maverick?: gpt-oss-120b is faster at 82 output tokens per second, against 13. Time to first token: 0.5 s for gpt-oss-120b, 0.7 s for Llama 4 Maverick.
Which has the larger context window, gpt-oss-120b or Llama 4 Maverick?: Llama 4 Maverick, with 524k tokens against 131k.