Wait Which Model?
← Back to directory
OpenAI

gpt-oss-120b

Released Aug 5, 2025 · knowledge cutoff 2024-06

Status
Superseded
Location
United States
Type
LLM
Modality
Text
Context window
131K
Max output
131K
Speed (high effort)
170 tok/s · 0.88s to first answer token
Price ($/MTok in / out)
$0.03 / $0.17
Cost per task
—
Open weights
Yes
Benchmarks6 of 10 reported

MMLU-Proretired

80.8%

GPQA Diamond

80.1%

SWE-bench Verified

62.4%

SWE-bench Pro

16.2%

AIME (latest)retired

92.5%

Humanity's Last Exam

14.9%

Terminal-Bench 2.1

—

LMArena Elo

—

GDPval-AA v2

—

ARC-AGI-2

—
Strengths & weaknesses

Strengths

  • Fits on a single 80GB datacenter GPU at native precision, so it's a genuinely self-hostable release rather than a paper-only open weights drop
  • Reasoning effort is a plain system-prompt string (low/medium/high), trading latency for depth without swapping checkpoints
  • Exposes its full chain-of-thought in the output rather than summarizing or hiding it, unlike OpenAI's closed reasoning models

Weaknesses

  • Hallucinates markedly more than OpenAI's closed models on people and fact lookups — the expected trade-off of a smaller open weight store of world knowledge
  • Locked to OpenAI's bespoke Harmony response format; feeding it a generic chat template silently breaks tool calls and reasoning
  • Inherited safety training leans toward refusal, and self-hosters report it overcorrecting on benign prompts

OpenAI's first open-weight release since GPT-2. GPQA Diamond 80.1%, HLE 14.9% and AIME 2025 92.5% are no-tools scores at high reasoning effort per OpenAI's model card (arXiv:2508.10925); with tools, GPQA rises to 80.9%, HLE to 19.0%, AIME to 97.9%. MMLU-Pro 80.8 is from the official Hugging Face model card. Terminal-Bench reported is 2.0 (18.7%), not the tracked 2.1 metric, so left null here. Pricing ($0.03/$0.17 per MTok) is a representative third-party hosted rate (OpenRouter/CoreWeave) — OpenAI's own API docs list the model with no attached price, and rates vary roughly 9x across hosts (e.g. AWS Bedrock charges $0.15/$0.60). SWE-bench Pro 16.2% is Scale's public-set leaderboard figure (also Table 1 of the SWE-Bench Pro paper) — third-party, not OpenAI-reported.

For developers

API model strings

  • openaigpt-oss-120b
  • aws-bedrockopenai.gpt-oss-120b-1:0

Licence

Apache License 2.0 · Permissive · commercial use permitted

Retirement

No retirement announced

Lineage

No recorded predecessor

News