Skip to main content
BenchLM
Data

Data as of October 17, 2026 · How the score is built

EstablishedOpen WeightNon-Reasoning

Released Aug 5, 2025128K context

GPT-OSS 120B

Decision readingGPT-OSS 120B scores 37.3 out of 100 and ranks #152 of 224. This profile shows 8 source-displayable benchmark rows; its strongest eligible category is Agentic at #110. Published weights can be self-hosted, but infrastructure cost varies and is not a comparable API token rate.

Released Aug 5, 2025 — see all recent releases

Find alternativesCompare GPT-OSS 120B
Share or export
Share on XLinkedIn
Social cardBenchmarks CSVAPI/MCP query guide

Decision snapshot

Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.

Capability

37.3/100

field median 49.6#152 of 224 ranked models

Public

#152of 224

Verified #75 of 88

Price

Self-hosted; infrastructure cost varies

input median $0.75No comparable first-party hosted token rate

Speed

214tok/s

field median 92 tok/sFirst token 10.21 s

Context

128Ktokens

field median 256,000Reported for this model; direct source link not stored

Strongest published evidence

Agentic ranks #110. Particularly useful for coding agents, browser research, and computer-use workflows.

Validate before choosing

8 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.

Source-linked · 8 displayable benchmark rows

Category score record

Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #110 of 128Percentile 14thWeight 22%1 benchmarkVerified
19.5
CodingRank #111 of 150Percentile 26thWeight 20%2 benchmarksVerified
23.0
ReasoningWeight 17%0 benchmarksNot measured
Not measured
MultimodalWeight 12%0 benchmarksNot measured
Not measured
KnowledgeRank #122 of 184Percentile 34thWeight 12%3 benchmarksVerified
38.6
MultilingualWeight 7%0 benchmarksNot measured
Not measured
Inst. FollowingWeight 5%0 benchmarksNot measured
Not measured
MathWeight 5%2 benchmarksVerified
Score pending

8 of 681 tracked benchmark slots have displayable evidence · bars run 0–100

Coverage details

How much of this is verified

Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.

  1. Agentic1/1 verified
  2. Coding2/2 verified
  3. ReasoningNot measured
  4. MultimodalNot measured
  5. Knowledge3/3 verified
  6. MultilingualNot measured
  7. Inst. FollowingNot measured
  8. Math2/2 verified
Verified sourceProvisionalNot measured

Capability shape

Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.

GPT-OSS 120B category percentile values

  • Agentic14th percentile
  • Coding26th percentile
  • ReasoningNot eligible
  • MultimodalNot eligible
  • Knowledge34th percentile
  • MultilingualNot eligible
  • Instruction followingNot eligible
  • MathNot eligible

The dashed outline is median of 6 nearest peers.

Eligible category ranks

  1. Agentic#110/128
  2. Coding#111/150
  3. ReasoningNot ranked
  4. MultimodalNot ranked
  5. Knowledge#122/184
  6. MultilingualNot ranked
  7. Inst. FollowingNot ranked
  8. MathNot ranked
Top decileTop quartileMid-fieldNot eligible

Benchmark ledger

Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.

Coding2 rows
Coding benchmark values, best verified comparison, weight, and source status
SWE-bench VerifiedSoftware Engineering Benchmark VerifiedScore62.4%Versus best verified row

Best verified: Claude Opus 5 · 96%

Gap33.6 behindWeightDisplay only
Provider exact
OpenAI: gpt-oss-120b and gpt-oss-20b model card
React Native EvalsScore71.6%Versus best verified row

Best verified: Composer 2 · 96.1%

Gap24.5 behindWeightDisplay only
Benchmark exact
React Native Evals leaderboard
Agentic1 row
Agentic benchmark values, best verified comparison, weight, and source status
Gert LabsGert Labs Composite Game BenchmarkScore29.61%Versus best verified row

Best verified: Claude Opus 4.8 · 72.97%

Gap43.4 behindWeightDisplay only
Benchmark exact
Gert Labs rankings
Knowledge3 rows
Knowledge benchmark values, best verified comparison, weight, and source status
HLEHumanity's Last ExamScore14.9%Versus best verified row

Best verified: Claude Fable 5.1 · 65%

Gap50.1 behindWeight44% ref. weight
Provider exact
OpenAI: gpt-oss-120b and gpt-oss-20b model card
GPQAGraduate-Level Google-Proof Q&AScore80.1%Versus best verified row

Best verified: GPT-6 Astra · 96%

Gap15.9 behindWeight3% ref. weight
Provider exact
OpenAI: gpt-oss-120b and gpt-oss-20b model card
MMLUMassive Multitask Language UnderstandingScore90%Versus best verified row

Best verified: o1 · 91.8%

Gap1.8 behindWeightDisplay only
Provider exact
OpenAI: gpt-oss-120b and gpt-oss-20b model card
Math2 rows
Math benchmark values, best verified comparison, weight, and source status
AIME 2024American Invitational Mathematics Examination 2024Score95.8%Versus best verified row

Best verified: GPT-OSS 120B · 95.8%

GapBest verifiedWeightDisplay only
Provider exact
OpenAI: gpt-oss-120b and gpt-oss-20b model card
AIME 2025American Invitational Mathematics Examination 2025Score92.5%Versus best verified row

Best verified: GPT-5.2 · 100%

Gap7.5 behindWeightDisplay only
Provider exact
OpenAI: gpt-oss-120b and gpt-oss-20b model card

Bars run 0–100; the dark tick marks the best source-verified value

All 8 rows

Lineage

The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.

  1. Aug 5, 2025 · you are here

    GPT-OSS 120B

    Score 37.3 · Price not listed

Base entry

GPT-OSS 20B · 33.3

Spec sheet

Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.

API model ID
Not published
Context window
128K
Maximum output
Not sourced yet
Knowledge cutoff
Not sourced yet
Input modalities
Not sourced yet
Output modalities
Not sourced yet
Parameters
Not sourced yet
Availability
Not sourced yet
Cloud regions
Not tracked yet
Lifecycle
Established
API capabilities
Tool calling, structured outputs, and batch support are not tracked yet
Prompt caching
Not documented in the pricing record
Self-host
GPT-OSS 120B needs ~80GB VRAM (1× NVIDIA H100 (80GB)).
Rate limits
Not tracked yet

How to read this profile

The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.

GPT-OSS 120B ranks #152 of 224 on the public leaderboard with a score of 37.32/100. Its source-verified position is #75 of 88.

GPT-OSS 120B is a open weight model with a 128K context window. No explicit reasoning mode is documented in this profile.

GPT-OSS 120B sits in the GPT-OSS family with GPT-OSS 20B. 8 of 681 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.

Its strongest eligible category is Agentic at #110, while its lowest eligible position is Knowledge at #122. particularly useful for coding agents, browser research, and computer-use workflows.

Last updated October 17, 2026. Runtime fields remain blank until a sourced snapshot exists.

Deployment options

Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

GPT-OSS 120B
API / mo$0
Self-host / mo$3,495
Break-even—
Model the full break-even

Questions

How does GPT-OSS 120B perform overall in AI benchmarks?

GPT-OSS 120B ranks #152 out of 224 models on the public BenchAlign leaderboard, with a score of 37.32/100. Its evidence status is Supported, and this profile shows 8 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.

Is GPT-OSS 120B good for knowledge and understanding?

GPT-OSS 120B ranks #122 out of 184 eligible models for knowledge and understanding, with a public category score of 38.6/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is GPT-OSS 120B good for coding and programming?

GPT-OSS 120B ranks #111 out of 150 eligible models for coding and programming, with a public category score of 23/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is GPT-OSS 120B good for mathematics?

GPT-OSS 120B has source-displayable benchmark coverage for mathematics, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Is GPT-OSS 120B good for agentic tool use and computer tasks?

GPT-OSS 120B ranks #110 out of 128 eligible models for agentic tool use and computer tasks, with a public category score of 19.5/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is GPT-OSS 120B open source?

GPT-OSS 120B is an open-weight model from OpenAI. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.

Which sibling models are related to GPT-OSS 120B?

GPT-OSS 120B belongs to the GPT-OSS family. Related tracked variants include GPT-OSS 20B. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.

Does GPT-OSS 120B have full benchmark coverage on BenchLM?

No. GPT-OSS 120B currently has 25 source-displayable rows across 681 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.

What is the context window size of GPT-OSS 120B?

GPT-OSS 120B has a reported context window of 128K in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.

Watch GPT-OSS 120B in the weekly brief

Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.

Read a sample issue

Join 5,600+ readers.

Compare GPT-OSS 120B with every tracked model953 comparisons