gpt-oss-120b vs o3

o3 leads gpt-oss-120b on the Artificial Analysis Intelligence Index, 20.2 to 11.6, and gpt-oss-120b costs 16.0x less per output token ($0.50 vs $8.00 per million). Updated October 22, 2026; 71 benchmarks have a result for both.

Replace gpt-oss-120b Replace o3

gpt-oss-120bOpenAI

Coding: No data
Overall: 50.0
Output $/M: $0.50

o3OpenAI

Coding: No data
Overall: 51.1
Output $/M: $8.00

vs boards won of 71 shared

gpt-oss-120b or o3: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick gpt-oss-120b for output tokens 16.0x cheaper ($0.50 vs $8.00 per million) and a lower cost per solved task ($0.51 against $0.571).

Model Agpt-oss-120bOpenAINot benchmarked1 independent benchmark$0.51 per solved task Model Bo3OpenAINot benchmarkedNo coding benchmark$0.571 per solved task

711031

Shared results: 71
gpt-oss-120b only: 10
o3 only: 31
Like-for-like categories: 8 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
o3
o3 leads, 20.2 against 11.6.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only gpt-oss-120b has a AA Agentic Index result, 3.7.
Directional only
Reasoning
GPQA Diamond
o3
o3 leads, 84.1% against 78.5%.
Same board, both measured
Math
AIME
gpt-oss-120b
gpt-oss-120b leads, 92.6% against 85.3%.
Same board, both measured
Knowledge
MMLU Pro
o3
o3 leads, 85.6% against 79.2%.
Same board, both measured
Web design
Design Arena: websites
o3
o3 leads, 1036 against 967.
Same board, both measured
Long documents
Listed context window
o3
o3 takes 200K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
gpt-oss-120b
gpt-oss-120b $0.0003, o3 $0.0060 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
gpt-oss-120b
gpt-oss-120b $0.51, o3 $0.571.
Published attempt cost and pass rate

At a glance

Coding index: gpt-oss-120b not benchmarked, o3 not benchmarked.
Widest category: Coding, 12.0 points apart on average over 10 shared benchmarks.
Widest single gap: Fiction.LiveBench: gpt-oss-120b 44.4% against o3 88.9%, 44.5 points apart on a 0 to 100 scale.
Output price: gpt-oss-120b $0.50 against o3 $8.00 per million output tokens, 16.0x apart.
Context window: gpt-oss-120b takes 131K tokens, o3 200K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
Category	gpt-oss-120b	o3
Coding	1	9
Intelligence	0	2
Agentic work	1	2
Reasoning	0	10
Math	6	2
Knowledge	0	10
Web design	0	5
General	0	23
All shared boards	8	63

CodingLike-for-likeSix of these boards feed the Vibe Coding Index19

Coding benchmarks for gpt-oss-120b and o3
Benchmark	gpt-oss-120b	o3	Leader
Aider polyglot	41.8%	81.3%	o3
SWE-bench Verified	26.0%	58.4%	o3
SWE-bench Multimodal	Not measured	36.0%	Only o3 measured
AA Coding Index	30.4	Not measured	Only gpt-oss-120b measured
LiveCodeBench (Vals AI)	83.2%	83.9%	o3
SWE-bench Verified (Vals AI)	33.6%	Not measured	Only gpt-oss-120b measured
LiveCodeBench (Artificial Analysis run)	87.8%	80.8%	gpt-oss-120b
SciCode	34.0%	Not measured	Only gpt-oss-120b measured
Terminal-Bench Hard (Artificial Analysis run)	23.5%	37.1%	o3
Terminal-Bench	18.7%	Not measured	Only gpt-oss-120b measured
GSO-Bench	Not measured	8.8%	Only o3 measured
WeirdML	48.2%	52.4%	o3
ALE-Bench	575.6	933.5	o3
LMArena Text: coding	1379	1407	o3
LMArena Text: software and IT	1387	1415	o3
SciCode	7.7%	9.2%	o3
Neither model has a result on the other 23 boards here

IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02

Intelligence benchmarks for gpt-oss-120b and o3
Benchmark	gpt-oss-120b	o3	Leader
AA Intelligence Index	11.6	20.2	o3
Epoch Capabilities Index	139.8	146.7	o3

Agentic workLike-for-likePublic boards, shown as published, kept out of the index12

Agentic work benchmarks for gpt-oss-120b and o3
Benchmark	gpt-oss-120b	o3	Leader
AA Agentic Index	3.7	Not measured	Only gpt-oss-120b measured
τ²-Bench Telecom	65.8%	80.7%	o3
APEX-Agents	4.4%	Not measured	Only gpt-oss-120b measured
METR time horizons	56.6%	65.4%	o3
GDPval	Not measured	30.8%	Only o3 measured
DeepResearch Bench	Not measured	45.2%	Only o3 measured
OSWorld	Not measured	23.0%	Only o3 measured
Vending-Bench 2	-$22	Not measured	Only gpt-oss-120b measured
Berkeley Function Calling Leaderboard (BFCL)	Not measured	63.0%	Only o3 measured
BrowseComp-Plus	67.0%	65.9%	gpt-oss-120b
Neither model has a result on the other 31 boards here

ReasoningLike-for-likePublic boards, shown as published, kept out of the index010

Reasoning benchmarks for gpt-oss-120b and o3
Benchmark	gpt-oss-120b	o3	Leader
GPQA Diamond	78.5%	84.1%	o3
MMMU Pro (Vals AI)	Not measured	80.4%	Only o3 measured
GPQA Diamond (Artificial Analysis run)	78.2%	82.7%	o3
Humanity's Last Exam (Artificial Analysis run)	19.6%	20.1%	o3
GPQA Diamond (Epoch AI run)	75.8%	81.8%	o3
ARC-AGI	Not measured	60.8%	Only o3 measured
ARC-AGI-2	Not measured	6.5%	Only o3 measured
SimpleBench	22.1%	53.1%	o3
Chess puzzles	Not measured	37.0%	Only o3 measured
Mystery game puzzles	2.0%	29.0%	o3
VPCT	Not measured	52.0%	Only o3 measured
LMArena Text: hard prompts	1364	1402	o3
LMArena Text: expert	1356	1402	o3
LMArena Text: hard prompts in English	1368	1411	o3
LMArena Vision: diagrams	Not measured	1220	Only o3 measured
LMArena Vision: homework	Not measured	1234	Only o3 measured
Kagi LLM Benchmark	58.6%	67.6%	o3
Neither model has a result on the other 5 boards here

MathLike-for-likePublic boards, shown as published, kept out of the index62

Math benchmarks for gpt-oss-120b and o3
Benchmark	gpt-oss-120b	o3	Leader
AIME	92.6%	85.3%	gpt-oss-120b
MATH 500 (Vals AI)	94.8%	94.6%	gpt-oss-120b
MGSM (Vals AI)	92.0%	91.8%	gpt-oss-120b
AA Math Index	93.4	88.3	gpt-oss-120b
AIME 2025 (Artificial Analysis run)	93.4%	88.3%	gpt-oss-120b
OTIS Mock AIME	88.9%	84.4%	gpt-oss-120b
FrontierMath, tiers 1 to 3	Not measured	33.3%	Only o3 measured
MATH level 5	Not measured	97.8%	Only o3 measured
LMArena Text: math	1389	1426	o3
LMArena Text: mathematical work	1386	1423	o3
Neither model has a result on the other 3 boards here

KnowledgeLike-for-likePublic boards, shown as published, kept out of the index010

Knowledge benchmarks for gpt-oss-120b and o3
Benchmark	gpt-oss-120b	o3	Leader
MMLU Pro	79.2%	85.6%	o3
LegalBench (Vals AI)	75.9%	83.8%	o3
CaseLaw (Vals AI)	48.8%	Not measured	Only gpt-oss-120b measured
CorpFin (Vals AI)	58.2%	59.7%	o3
TaxEval (Vals AI)	71.6%	74.6%	o3
MortgageTax (Vals AI)	Not measured	65.7%	Only o3 measured
MedQA (Vals AI)	91.4%	96.1%	o3
MedCode (Vals AI)	Not measured	47.3%	Only o3 measured
MMLU Pro (Artificial Analysis run)	80.8%	85.3%	o3
SimpleQA Verified	Not measured	49.4%	Only o3 measured
GeoBench	Not measured	74.0%	Only o3 measured
LMArena Text: science	1382	1429	o3
LMArena Text: medicine and healthcare	1388	1448	o3
LMArena Text: legal and government	1355	1428	o3
LMArena Text: business and finance	1359	1393	o3
FACTS Benchmark Suite	Not measured	44.4%	Only o3 measured
Neither model has a result on the other 2 boards here

Web designLike-for-likePublic boards, shown as published, kept out of the index05

Web design benchmarks for gpt-oss-120b and o3
Benchmark	gpt-oss-120b	o3	Leader
Design Arena: websites	967	1036	o3
Design Arena: UI components	924	1017	o3
Design Arena: game dev	992	1034	o3
Design Arena: data viz	987	1200	o3
Design Arena: 3D	901	Not measured	Only gpt-oss-120b measured
Design Arena: all code categories	962	1020	o3
Neither model has a result on the other 3 boards here

GeneralLike-for-likePublic boards, shown as published, kept out of the index023

General benchmarks for gpt-oss-120b and o3
Benchmark	gpt-oss-120b	o3	Leader
SAGE (Vals AI)	Not measured	41.8%	Only o3 measured
MedScribe (Vals AI)	Not measured	76.7%	Only o3 measured
IFBench	69.0%	71.4%	o3
Long context reasoning (AA-LCR)	52.0%	74.7%	o3
DTBench	76.3%	84.8%	o3
LMCA	22.1%	39.7%	o3
Fiction.LiveBench	44.4%	88.9%	o3
Creative writing (Lech Mazur)	77.1%	83.9%	o3
CL-bench	Not measured	17.8%	Only o3 measured
Surface Evolver Bench	25.0%	Not measured	Only gpt-oss-120b measured
LMArena Text	1366	1410	o3
LMArena Text: instruction following	1318	1368	o3
LMArena Text: creative writing	1274	1359	o3
LMArena Vision	Not measured	1214	Only o3 measured
LMArena Text: English	1375	1417	o3
LMArena Text: non-English	1351	1401	o3
LMArena Text: Chinese	1385	1437	o3
LMArena Text: German	1353	1420	o3
LMArena Text: Japanese	1331	1403	o3
LMArena Text: Korean	1282	1370	o3
LMArena Text: French	1370	1430	o3
LMArena Text: Spanish	1389	1395	o3
LMArena Text: Russian	1343	1406	o3
LMArena Text: Polish	1353	1438	o3
LMArena Text: multi-turn	1340	1405	o3
LMArena Text: longer queries	1319	1372	o3
LMArena Text: writing and language	1306	1372	o3
LMArena Text: entertainment and media	1292	1373	o3
LMArena Vision: English	Not measured	1221	Only o3 measured
LMArena Vision: Chinese	Not measured	1237	Only o3 measured
LMArena Vision: reading text	Not measured	1218	Only o3 measured
LMArena Vision: humor	Not measured	1222	Only o3 measured
LMArena Vision: captioning	Not measured	1210	Only o3 measured
LMArena Vision: recognizing things	Not measured	1234	Only o3 measured
LMArena Vision: creative writing	Not measured	1201	Only o3 measured
Neither model has a result on the other 11 boards here

Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared

Image generation benchmarks for gpt-oss-120b and o3
Benchmark	gpt-oss-120b	o3	Leader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

gpt-oss-120b$0.0003Fits in one request

o3$0.0060Fits in one request

gpt-oss-120b costs less

Repository review

50K input + 3K output tokens

gpt-oss-120b$0.0065Fits in one request

o3$0.124Fits in one request

gpt-oss-120b costs less

Agent loop

200K input + 10K output tokens

gpt-oss-120b$0.025Exceeds the context window

o3$0.480Exceeds the context window

gpt-oss-120b costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of gpt-oss-120b and o3
Specification	OpenAI gpt-oss-120b	OpenAI o3
Maker	OpenAI	OpenAI
Weights	Open weights	No public weights listed
Released	August 5, 2025	April 16, 2025
Context window	131K	200K
Input $/Mtok	$0.10	$2.00
Output $/Mtok	$0.50	$8.00
Coding index	Not benchmarked	Not benchmarked
Independent measurements behind it	1	0
Cost per solved task	$0.51	$0.571
Source	OpenRouter listing	OpenRouter listing

Questions

Is gpt-oss-120b better than o3 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick gpt-oss-120b for output tokens 16.0x cheaper ($0.50 vs $8.00 per million) and a lower cost per solved task ($0.51 against $0.571).

Which is cheaper, gpt-oss-120b or o3?

gpt-oss-120b costs $0.10 per million input tokens and $0.50 per million output tokens; o3 costs $2.00 and $8.00. Per solved SWE-bench Verified task, gpt-oss-120b costs $0.51 and o3 $0.571.

Which has the bigger context window, gpt-oss-120b or o3?

o3, with 200K tokens against 131K.

How many benchmarks is the gpt-oss-120b vs o3 comparison based on?

71 benchmarks have a result for both models as of October 22, 2026. gpt-oss-120b's coding index rests on 1 independent benchmark and o3's on 0. Where only one model has a result, the page says so instead of naming a winner.

gpt-oss-120b or o3: which to pick

Which one for your work

Coding

Intelligence

Agentic work

Reasoning

Math

Knowledge

Web design

Long documents

Everyday cost

Cost per solved task

At a glance

Benchmark by benchmark

What each workload costs

Chat turn

Repository review

Agent loop

Specification differences

Questions

Compare next