Enter opens the highlighted result. Esc closes.

Claude Opus 4.5 vs gpt-oss-120b

Claude Opus 4.5 leads gpt-oss-120b on the Artificial Analysis Intelligence Index, 29.1 to 11.6, and gpt-oss-120b costs 50.0x less per output token ($0.50 vs $25.00 per million). Updated October 22, 2026; 72 benchmarks have a result for both.

Replace Claude Opus 4.5 Replace gpt-oss-120b
Claude Opus 4.5Anthropic
Coding
44.0
Overall
55.7
Output $/M
$25.00
67
gpt-oss-120bOpenAI
Coding
No data
Overall
50.0
Output $/M
$0.50
5
vs boards won of 72 shared

Claude Opus 4.5 or gpt-oss-120b: which to pick

Only Claude Opus 4.5 has a coding score, 44.0 on the Vibe Coding Index; gpt-oss-120b has none, so the two cannot be ranked on coding.

Pick gpt-oss-120b for output tokens 50.0x cheaper ($0.50 vs $25.00 per million) and a lower cost per solved task ($0.51 against $1.37).

Model AClaude Opus 4.5Anthropic44.0/1003 independent benchmarks$1.37 per solved taskModel Bgpt-oss-120bOpenAINot benchmarked1 independent benchmark$0.51 per solved task
Shared results
72
Claude Opus 4.5 only
40
gpt-oss-120b only
13
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.

At a glance

Coding index
Claude Opus 4.5 44.0 from 3 benchmarks, gpt-oss-120b not benchmarked.
Widest category
Web design, 34.9 points apart on average over 6 shared benchmarks.
Widest single gap
SWE-bench Verified: Claude Opus 4.5 79.2% against gpt-oss-120b 26.0%, 53.2 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.5 $25.00 against gpt-oss-120b $0.50 per million output tokens, 50.0x apart.
Context window
Claude Opus 4.5 takes 200K tokens, gpt-oss-120b 131K.

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
CategoryClaude Opus 4.5Barsgpt-oss-120bTies
Coding81
Intelligence20
Agentic work30
Reasoning100
Math43
Knowledge130
Web design60
General211
All shared boards675
CodingLike-for-likeSix of these boards feed the Vibe Coding Index81
Coding benchmarks for Claude Opus 4.5 and gpt-oss-120b
BenchmarkClaude Opus 4.5gpt-oss-120bLeader
Aider polyglotNot measured41.8%Only gpt-oss-120b measured
SWE-bench Verified79.2%26.0%Claude Opus 4.5
SWE-bench (full test set)52.6%Not measuredOnly Claude Opus 4.5 measured
SWE-bench Multilingual70.7%Not measuredOnly Claude Opus 4.5 measured
LMArena WebDev1494Not measuredOnly Claude Opus 4.5 measured
AA Coding IndexNot measured30.4Only gpt-oss-120b measured
LiveCodeBench (Vals AI)83.7%83.2%Claude Opus 4.5
SWE-bench Verified (Vals AI)76.4%33.6%Claude Opus 4.5
Vibe Code Bench (Vals AI)20.6%Not measuredOnly Claude Opus 4.5 measured
LiveCodeBench (Artificial Analysis run)87.1%87.8%gpt-oss-120b
SciCodeNot measured34.0%Only gpt-oss-120b measured
Terminal-Bench Hard (Artificial Analysis run)47.0%23.5%Claude Opus 4.5
Terminal-Bench63.1%18.7%Claude Opus 4.5
GSO-Bench26.5%Not measuredOnly Claude Opus 4.5 measured
WeirdML63.7%48.2%Claude Opus 4.5
Cybench82.0%Not measuredOnly Claude Opus 4.5 measured
ALE-BenchNot measured575.6Only gpt-oss-120b measured
LMArena Text: coding15031379Claude Opus 4.5
LMArena Text: software and IT14831387Claude Opus 4.5
LMArena WebDev: React1478Not measuredOnly Claude Opus 4.5 measured
LMArena WebDev: HTML1510Not measuredOnly Claude Opus 4.5 measured
SciCodeNot measured7.7%Only gpt-oss-120b measured
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 4.5 and gpt-oss-120b
BenchmarkClaude Opus 4.5gpt-oss-120bLeader
AA Intelligence Index29.111.6Claude Opus 4.5
Epoch Capabilities Index150.1139.8Claude Opus 4.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index30
Agentic work benchmarks for Claude Opus 4.5 and gpt-oss-120b
BenchmarkClaude Opus 4.5gpt-oss-120bLeader
AA Agentic IndexNot measured3.7Only gpt-oss-120b measured
Design Arena: agents building web apps1159Not measuredOnly Claude Opus 4.5 measured
Design Arena: agents building full-stack apps1156Not measuredOnly Claude Opus 4.5 measured
Design Arena: agents building mobile apps1188Not measuredOnly Claude Opus 4.5 measured
Design Arena: agents building Android apps1176Not measuredOnly Claude Opus 4.5 measured
τ²-Bench Telecom89.5%65.8%Claude Opus 4.5
APEX-AgentsNot measured4.4%Only gpt-oss-120b measured
METR time horizons75.0%56.6%Claude Opus 4.5
Remote Labor Index3.8%Not measuredOnly Claude Opus 4.5 measured
GDPval45.5%Not measuredOnly Claude Opus 4.5 measured
BALROG43.5%Not measuredOnly Claude Opus 4.5 measured
DeepResearch Bench54.8%Not measuredOnly Claude Opus 4.5 measured
OSWorld66.3%Not measuredOnly Claude Opus 4.5 measured
Vending-Bench 2$4,967-$22Claude Opus 4.5
Berkeley Function Calling Leaderboard (BFCL)77.5%Not measuredOnly Claude Opus 4.5 measured
BrowseComp-PlusNot measured67.0%Only gpt-oss-120b measured
MCP Atlas69.8%Not measuredOnly Claude Opus 4.5 measured
Neither model has a result on the other 25 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index100
Reasoning benchmarks for Claude Opus 4.5 and gpt-oss-120b
BenchmarkClaude Opus 4.5gpt-oss-120bLeader
GPQA Diamond85.9%78.5%Claude Opus 4.5
MMMU Pro (Vals AI)83.0%Not measuredOnly Claude Opus 4.5 measured
GPQA Diamond (Artificial Analysis run)86.6%78.2%Claude Opus 4.5
Humanity's Last Exam (Artificial Analysis run)30.1%19.6%Claude Opus 4.5
GPQA Diamond (Epoch AI run)86.0%75.8%Claude Opus 4.5
ARC-AGI80.0%Not measuredOnly Claude Opus 4.5 measured
ARC-AGI-237.6%Not measuredOnly Claude Opus 4.5 measured
SimpleBench62.0%22.1%Claude Opus 4.5
Chess puzzles14.0%Not measuredOnly Claude Opus 4.5 measured
Mystery game puzzles22.0%2.0%Claude Opus 4.5
EBR-bench14.3%Not measuredOnly Claude Opus 4.5 measured
VPCT40.0%Not measuredOnly Claude Opus 4.5 measured
LMArena Text: hard prompts14761364Claude Opus 4.5
LMArena Text: expert14871356Claude Opus 4.5
LMArena Text: hard prompts in English14821368Claude Opus 4.5
Kagi LLM Benchmark80.2%58.6%Claude Opus 4.5
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index43
Math benchmarks for Claude Opus 4.5 and gpt-oss-120b
BenchmarkClaude Opus 4.5gpt-oss-120bLeader
AIME95.4%92.6%Claude Opus 4.5
MATH 500 (Vals AI)Not measured94.8%Only gpt-oss-120b measured
MGSM (Vals AI)95.2%92.0%Claude Opus 4.5
AA Math Index91.393.4gpt-oss-120b
AIME 2025 (Artificial Analysis run)91.3%93.4%gpt-oss-120b
OTIS Mock AIME86.1%88.9%gpt-oss-120b
FrontierMath, tiers 1 to 334.4%Not measuredOnly Claude Opus 4.5 measured
FrontierMath, tier 44.9%Not measuredOnly Claude Opus 4.5 measured
ProofBench36.0%Not measuredOnly Claude Opus 4.5 measured
LMArena Text: math14631389Claude Opus 4.5
LMArena Text: mathematical work14681386Claude Opus 4.5
MathArenaNot measured15.1%Only gpt-oss-120b measured
Neither model has a result on the other 2 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index130
Knowledge benchmarks for Claude Opus 4.5 and gpt-oss-120b
BenchmarkClaude Opus 4.5gpt-oss-120bLeader
MMLU Pro87.3%79.2%Claude Opus 4.5
LegalBench (Vals AI)84.6%75.9%Claude Opus 4.5
CaseLaw (Vals AI)62.6%48.8%Claude Opus 4.5
CorpFin (Vals AI)65.1%58.2%Claude Opus 4.5
TaxEval (Vals AI)74.9%71.6%Claude Opus 4.5
MortgageTax (Vals AI)68.7%Not measuredOnly Claude Opus 4.5 measured
MedQA (Vals AI)95.9%91.4%Claude Opus 4.5
MedCode (Vals AI)49.2%Not measuredOnly Claude Opus 4.5 measured
MMLU Pro (Artificial Analysis run)89.5%80.8%Claude Opus 4.5
SimpleQA Verified45.7%Not measuredOnly Claude Opus 4.5 measured
GeoBench75.0%Not measuredOnly Claude Opus 4.5 measured
LMArena Text: science14541382Claude Opus 4.5
LMArena Text: medicine and healthcare14441388Claude Opus 4.5
LMArena Text: legal and government14591355Claude Opus 4.5
LMArena Text: business and finance14481359Claude Opus 4.5
FACTS Benchmark Suite43.9%Not measuredOnly Claude Opus 4.5 measured
PRBench Finance46.2%43.8%Claude Opus 4.5
PRBench Legal44.2%40.2%Claude Opus 4.5
Neither model has a result on the other 2 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for Claude Opus 4.5 and gpt-oss-120b
BenchmarkClaude Opus 4.5gpt-oss-120bLeader
Design Arena: websites1247968Claude Opus 4.5
Design Arena: UI components1236924Claude Opus 4.5
Design Arena: game dev1228991Claude Opus 4.5
Design Arena: data viz1243987Claude Opus 4.5
Design Arena: 3D1213901Claude Opus 4.5
Design Arena: all code categories1241962Claude Opus 4.5
Design Arena: SVG1180Not measuredOnly Claude Opus 4.5 measured
Design Arena: ASCII art1190Not measuredOnly Claude Opus 4.5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index211
General benchmarks for Claude Opus 4.5 and gpt-oss-120b
BenchmarkClaude Opus 4.5gpt-oss-120bLeader
SAGE (Vals AI)52.1%Not measuredOnly Claude Opus 4.5 measured
MedScribe (Vals AI)85.3%Not measuredOnly Claude Opus 4.5 measured
IFBench58.0%69.0%gpt-oss-120b
Long context reasoning (AA-LCR)77.3%52.0%Claude Opus 4.5
DTBench89.9%76.3%Claude Opus 4.5
LMCA44.5%22.1%Claude Opus 4.5
Fiction.LiveBenchNot measured44.4%Only gpt-oss-120b measured
Creative writing (Lech Mazur)Not measured77.1%Only gpt-oss-120b measured
CL-bench21.1%Not measuredOnly Claude Opus 4.5 measured
Surface Evolver BenchNot measured25.0%Only gpt-oss-120b measured
Furniture assembly28.3%Not measuredOnly Claude Opus 4.5 measured
LMArena Text14511366Claude Opus 4.5
LMArena Text: instruction following14781318Claude Opus 4.5
LMArena Text: creative writing14451274Claude Opus 4.5
LMArena Text: English14611375Claude Opus 4.5
LMArena Text: non-English14381351Claude Opus 4.5
LMArena Text: Chinese14701385Claude Opus 4.5
LMArena Text: German14491353Claude Opus 4.5
LMArena Text: Japanese14171331Claude Opus 4.5
LMArena Text: Korean14241282Claude Opus 4.5
LMArena Text: French14711370Claude Opus 4.5
LMArena Text: Spanish14571389Claude Opus 4.5
LMArena Text: Russian14471343Claude Opus 4.5
LMArena Text: Polish14391353Claude Opus 4.5
LMArena Text: multi-turn14661340Claude Opus 4.5
LMArena Text: longer queries14791319Claude Opus 4.5
LMArena Text: writing and language14521306Claude Opus 4.5
LMArena Text: entertainment and media14341292Claude Opus 4.5
LMArena Document1462Not measuredOnly Claude Opus 4.5 measured
MultiChallenge59.0%45.3%Claude Opus 4.5
Neither model has a result on the other 18 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Opus 4.5 and gpt-oss-120b
BenchmarkClaude Opus 4.5gpt-oss-120bLeader
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

Claude Opus 4.5$0.018Fits in one request
gpt-oss-120b$0.0003Fits in one request

gpt-oss-120b costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.5$0.325Fits in one request
gpt-oss-120b$0.0065Fits in one request

gpt-oss-120b costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.5$1.25Exceeds the context window
gpt-oss-120b$0.025Exceeds 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 Claude Opus 4.5 and gpt-oss-120b
SpecificationAnthropic Claude Opus 4.5OpenAI gpt-oss-120b
MakerAnthropicOpenAI
WeightsNo public weights listedOpen weights
ReleasedNovember 24, 2025August 5, 2025
Context window200K131K
Input $/Mtok$5.00$0.10
Output $/Mtok$25.00$0.50
Coding index44.0Not benchmarked
Independent measurements behind it31
Cost per solved task$1.37$0.51
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.5 better than gpt-oss-120b for coding?

Only Claude Opus 4.5 has a coding score, 44.0 on the Vibe Coding Index; gpt-oss-120b has none, so the two cannot be ranked on coding. Pick gpt-oss-120b for output tokens 50.0x cheaper ($0.50 vs $25.00 per million) and a lower cost per solved task ($0.51 against $1.37).

Which is cheaper, Claude Opus 4.5 or gpt-oss-120b?

Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; gpt-oss-120b costs $0.10 and $0.50. Per solved SWE-bench Verified task, Claude Opus 4.5 costs $1.37 and gpt-oss-120b $0.51.

Which has the bigger context window, Claude Opus 4.5 or gpt-oss-120b?

Claude Opus 4.5, with 200K tokens against 131K.

How many benchmarks is the Claude Opus 4.5 vs gpt-oss-120b comparison based on?

72 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.5's coding index rests on 3 independent benchmarks and gpt-oss-120b's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next