Skip to main content

Model profile

GPT-OSS 120B

OpenAIEstablishedReleased Aug 5, 2025
Data verified
Overall Score
50.08Public #116 of 200Verified #63 of 99
Arena Elo
1353
Eligible category ranks
3of 8
Price (1M tokens)
$0 in / $0 out
API pricing
Speed
262tok/s
Context
128K

Evidence coverage

27 of 321 tracked benchmarks are published. 2 are verified and 25 provisional. 8 of 8 categories are measured.

Updated July 20, 2026Methodology
Published / tracked
27 / 321
Verified
2
Provisional
25
Categories with evidence
8 / 8

Evidence by category

  • Agentic9 benchmarks
    Mixed evidence
  • Coding4 benchmarks
    Mixed evidence
  • Reasoning2 benchmarks
    Reported
  • Knowledge8 benchmarks
    Reported
  • Math1 benchmark
    Reported
  • Multilingual1 benchmark
    Reported
  • Multimodal1 benchmark
    Reported
  • Inst. Following1 benchmark
    Reported
Open WeightSelf-hostNon-Reasoning
Confidence:
Low
base

GPT-OSS 120B ranks #116 out of 200 models on the public leaderboard with an overall score of 50.08/100. It also ranks #63 out of 99 on the verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

GPT-OSS 120B is a open weight model with a 128K token context window. It processes queries without explicit chain-of-thought reasoning, offering faster response times and lower token usage.

GPT-OSS 120B sits inside the GPT-OSS family alongside GPT-OSS 20B. This profile currently has 27 of 321 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Knowledge (#32), while its weakest is Coding (#80). This performance profile makes it particularly effective for knowledge-intensive tasks like research, analysis, and factual Q&A.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 49.8950.28

  1. DeepSeek Coder 2.0
    DeepSeek
    #11450.28
    DeepSeek Coder 2.0 is #114 with a score of 50.28.
    Compare
  2. Seed 1.6
    ByteDance
    #11550.23
    Seed 1.6 is #115 with a score of 50.23.
    Compare
  3. GPT-OSS 120BCurrent model
    OpenAI
    #11650.08
    GPT-OSS 120B is #116 with a score of 50.08.
  4. Nemotron 3 Super 100B
    NVIDIA
    #11750.08
    Nemotron 3 Super 100B is #117 with a score of 50.08.
    Compare
  5. o4-mini (high)
    OpenAI
    #11849.98
    o4-mini (high) is #118 with a score of 49.98.
    Compare
  6. DeepSeekMath V2
    DeepSeek
    #11949.89
    DeepSeekMath V2 is #119 with a score of 49.89.
    Compare
  7. Qwen2.5-1M
    Alibaba
    #12049.89
    Qwen2.5-1M is #120 with a score of 49.89.
    Compare

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

  1. Knowledge39%
    Eligible cohort rank #32 of 52Category score 66.6
  2. Agentic36%
    Eligible cohort rank #76 of 119Category score 44.9
  3. Coding35%
    Eligible cohort rank #80 of 122Category score 47.5

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #76 of 119Percentile 36thWeight 22%9 benchmarksMixed sources44.9
CodingRank #80 of 122Percentile 35thWeight 20%4 benchmarksMixed sources47.5
ReasoningRank Not rankedWeight 17%2 benchmarksReported58.4
KnowledgeRank #32 of 52Percentile 39thWeight 12%8 benchmarksReported66.6
MathWeight 5%1 benchmarkReportedScore pending
MultilingualRank Not rankedWeight 7%1 benchmarkReported70.0
MultimodalRank Not rankedWeight 12%1 benchmarkReported48.0
Inst. FollowingRank Not rankedWeight 5%1 benchmarkReported79.0

Chatbot Arena performance

Scroll horizontally to inspect confidence intervals and vote counts.

Chatbot Arena Elo, confidence interval, and vote count by evaluation view
ViewEloConfidence intervalVotes
Text Overall1353±4.330,629
Coding1390±7.76,491
Math1382±13.61,795
Instruction Following1325±7.07,817
Creative Writing1278±9.83,950
Multi-turn1328±8.75,003
Hard Prompts1362±5.714,765
Hard Prompts (English)1367±7.27,634
Longer Query1324±7.86,458

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic9 benchmarks
AA Agentic IndexReported

Artificial Analysis Agentic Index

13.2%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
APEX-Agents-AAReported
3.1%Display only
Source: Artificial Analysis: apex-agents-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
τ²-bench resultsReported

τ²-Bench Tool-Agent-User Evaluation

65.8%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
GDPval-AAReported

GDPval-AA normalized

15.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
GDPval-AAReported
799Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Gert LabsBenchmark exact

Gert Labs Composite Game Benchmark

29.61%Display only
Source: Gert Labs rankingsProvenance: Gert Labs reports this composite leaderboard score in the public rankings API. BenchLM scales the source gscore from 0-1 to 0-100 and stores it as a display-only agentic benchmark.
AA EnterpriseOps-GymReported

Artificial Analysis EnterpriseOps-Gym

25.5%Display only
Source: Artificial Analysis: enterprise-ops-gym-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA Harvey LABReported

Artificial Analysis Harvey LAB-AA

0.0%Display only
Source: Artificial Analysis: harvey-lab-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA ITBenchReported

Artificial Analysis ITBench-AA

5.6%Display only
Source: Artificial Analysis: itbench-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Coding4 benchmarks
React Native EvalsBenchmark exact
71.6%Display only
Source: React Native Evals leaderboardProvenance: React Native Evals reports this exact overall score for GPT OSS 120B in the public dashboard run finished on 2026-04-28.
AA Coding IndexReported

Artificial Analysis Coding Index

30.4%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-SciCodeReported

Artificial Analysis SciCode

38.9%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA LiveCodeBenchReported

Artificial Analysis LiveCodeBench

87.8%Display only
Source: Artificial Analysis: livecodebench leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Reasoning2 benchmarks
AA-LCRReported

Artificial Analysis Long Context Reasoning

50.7%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
CritPtReported

Critical Physics Tasks

1.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Knowledge8 benchmarks
Artificial Analysis Intelligence IndexReported
23.8%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-GPQA DiamondReported

Artificial Analysis GPQA Diamond

78.2%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-HLEReported

Artificial Analysis Humanity's Last Exam

18.5%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience IndexReported

Artificial Analysis Omniscience Index

-50.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

21.5%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

91.2%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA Openness IndexReported

Artificial Analysis Openness Index

38.9%Display only
Source: Artificial Analysis: artificial-analysis-openness-index leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA MMLU-ProReported

Artificial Analysis MMLU-Pro

80.8%Display only
Source: Artificial Analysis: mmlu-pro leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Math1 benchmark
AA AIME 2025Reported

Artificial Analysis AIME 2025

93.4%Display only
Source: Artificial Analysis: aime-2025 leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Multilingual1 benchmark
AA Global-MMLU-LiteReported

Artificial Analysis Global-MMLU-Lite

82.8%Display only
Source: Artificial Analysis: global-mmlu-lite leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Multimodal1 benchmark
Design Arena WebsiteReported

Design Arena Website Elo

1000Display only
Source: OpenRouter model benchmarksProvenance: Display-only Design Arena Website Elo synced from OpenRouter model benchmark metadata. It is excluded from BenchLM weighted scoring.
Inst. Following1 benchmark
AA-IFBenchReported

Artificial Analysis IFBench

69.0%Display only
Source: Artificial Analysis: ifbench leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.

GPT-OSS Family

Base entry

Frequently Asked Questions

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

GPT-OSS 120B has 27 published benchmark scores on BenchLM, but it does not yet have enough non-generated coverage to receive a global overall rank.

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

GPT-OSS 120B ranks #32 out of 52 models in knowledge and understanding benchmarks with an average score of 66.6. There are stronger options in this category.

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

GPT-OSS 120B ranks #80 out of 122 models in coding and programming benchmarks with an average score of 47.5. There are stronger options in this category.

Is GPT-OSS 120B good for mathematics?

GPT-OSS 120B has visible benchmark coverage in mathematics, but BenchLM does not currently assign it a global category rank there.

Is GPT-OSS 120B good for reasoning and logic?

GPT-OSS 120B has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

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

GPT-OSS 120B ranks #76 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 44.9. There are stronger options in this category.

Is GPT-OSS 120B good for multimodal and grounded tasks?

GPT-OSS 120B has visible benchmark coverage in multimodal and grounded tasks, but BenchLM does not currently assign it a global category rank there.

Is GPT-OSS 120B good for instruction following?

GPT-OSS 120B has visible benchmark coverage in instruction following, but BenchLM does not currently assign it a global category rank there.

Is GPT-OSS 120B good for multilingual tasks?

GPT-OSS 120B has visible benchmark coverage in multilingual tasks, but BenchLM does not currently assign it a global category rank there.

Is GPT-OSS 120B open source?

Yes, GPT-OSS 120B is an open weight model created by OpenAI, meaning it can be downloaded and run locally or fine-tuned for specific use cases.

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

GPT-OSS 120B belongs to the GPT-OSS family. Related variants on BenchLM include GPT-OSS 20B.

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

Not yet. GPT-OSS 120B currently has 27 published benchmark scores out of the 321 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

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

GPT-OSS 120B has a published context window of 128K, which determines how much text it can process in a single interaction.

Last updated: July 20, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Choose with this week’s evidence

Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.

Free. One email per week.