Benchmark suiteLatest source data: Jun 10, 2026Checked: June 14, 2026

GPT Oss 120b.

A model-level benchmark profile for GPT Oss 120b, combining Arena category ranks, suite indexes, commercial price and speed data, SWE-bench status, and lab context.

OpenAI lab page

Lab

OpenAI

Open weights

Coverage

56%

5 of 9 tracked signals

Best Arena rank

#169

Text Arena

Best suite

Agents / 100

Model profile

Benchmark signal map.

This view treats missing values as coverage gaps, then puts every available score, rank, cost, and speed signal into the same visual hierarchy.

Analyst view

GPT Oss 120b is strongest on agents.

56% coverage

Its best composite result is rank #6 in the agents view, with a 100 agent proxy. The strongest raw Arena signal is Text Arena at rank #169 with 30,644 public votes.

Best current lane

Agents

#6 / 100 agent proxy

Strongest raw signal

Text

#169, 1353 score

Commercial posture

$0.262

0.51s first token / 353 tok/s

Coverage gaps

WebDev ArenaVision ArenaSearch ArenaDocument Arena

Profile completeness

5 of 9 signals matched

56%

Arena categories

1/5

Text

Commercial match

Live

gpt-oss-120b (high)

SWE-bench

#42

bash-only

Raw identifier

gpt-oss-120b

Open weights

Performance cockpit

Public benchmark scores

Arena rows show score, public rank, confidence interval, vote count, and publish date. Missing rows stay visible as coverage gaps.

Text Arena

Arena category

1,353#169

1348-1357 CI

30,644 votes

Jun 10, 2026

Arena public leaderboard dataset

WebDev Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

Vision Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

Search Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

Document Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

SWE-bench Verified

Software issue resolution

26%#42

bash-only

gpt-oss-120b

Aug 7, 2025

SWE-bench Verified

Cost and speed

Commercial profile

Price, latency, and throughput are only shown when a confident commercial source row is matched.

Blended price

$0.262

USD / 1M tokens

Input price

$0.150

USD / 1M input tokens

Output price

$0.600

USD / 1M output tokens

Latency

0.51s

Median time to first token

Output speed

353 tok/s

Median generation speed

Matched source row

gpt-oss-120b (high)

Suite position

Composite ranks by benchmark lens.

These views combine available public signals into purpose-specific indexes. A missing card means the model lacks enough source coverage for that lens.

Value

Quality, price, latency, and output speed

#2777

value index

blended / 1M tokens$0.262

time to first token0.51s

output speed353 tok/s

Coding

Code Arena, SWE-bench, and output speed

#7825

coding index

Code ArenaNot listed