OpenAI apache_2_0 Released Aug 5, 2025 Updated
GPT OSS 120B
ToolsGuide Scores, rankings, test results and price.
Model summary
- Text #174 / 416
268 / 1,000
ToolsGuide Score· votes 224, tests 332
- Price per 1M tokens
In $0.04· Out $0.17
$0.04
Input · median text model $0.43
Summary
GPT OSS 120B is OpenAI's model, released Aug 5, 2025. It's ranked in 1 category and does best at text: #174 of 416, with a ToolsGuide Score of 268 against a median of 235.
It costs $0.04 per million input tokens and $0.17 per million output tokens, below the median text model ($0.43).
It has published results on 7 tests.
Specifications
- Creator
- OpenAI
- Licence
- apache_2_0
- Released
- Aug 5, 2025
- Context window
- 131K tokens
- Input price
- $0.04 / 1M
- Output price
- $0.17 / 1M
- Tests reported
- 7
- Settings ranked
- gpt-oss-120b
Model comparison
Against the ten best text models.
Text score
ToolsGuide Score out of 1,000 · Higher is better
Input price
USD per 1M input tokens · Lower is better
Leaderboards
Where GPT OSS 120B sits among the top 20 in each category.
Text
#174 of 416 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model
By task
Scored from votes on each kind of prompt alone, on the same 1,000-point scale.
Score against price
Text · the 10 priced models ranked closest · up and to the left is better value
Against its nearest rivals
Text prompts by kind · ToolsGuide Score from votes · hover for values
- GPT OSS 120B
-
gemini-2.5-flash -
glm-4.5-air
Text
gpt-oss-120b · hover a bar for its rank
Test results
Every test GPT OSS 120B has a published result on, out of 100%, with its rank among the models that took it.
GPQA
#103 / 256Graduate-level science questions written to be hard to look up.
80.1%
Self-reported
Humanity's Last Exam
#84 / 108Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions
14.9%
Self-reported · In the text score· In the vision score
MMLU
#12 / 103Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
90.0%
Self-reported
TAU-bench Retail
#15 / 25A benchmark for evaluating tool-agent-user interaction in retail environments. Tests language agents' ability to handle dynamic conversations with users while using domain-specific API tools and following policy guidelines. Evaluates agents on tasks like order cancellations, address changes, and order status checks through multi-turn conversations.
67.8%
Self-reported
HealthBench Hard
#6 / 24A challenging variation of HealthBench that evaluates large language models' performance and safety in healthcare through 5,000 multi-turn conversations with particularly rigorous evaluation criteria validated by 262 physicians from 60 countries
30.0%
Self-reported
CodeForces
#10 / 20A competitive programming benchmark using problems from the CodeForces platform. The benchmark evaluates code generation capabilities of LLMs on algorithmic problems with difficulty ratings ranging from 800 to 2400. Problems cover diverse algorithmic categories including dynamic programming, graph algorithms, data structures, and mathematical problems with standardized evaluation through direct platform submission.
0.0%
Self-reported
HealthBench
#7 / 14An open-source benchmark for measuring performance and safety of large language models in healthcare, consisting of 5,000 multi-turn conversations evaluated by 262 physicians using 48,562 unique rubric criteria across health contexts and behavioral dimensions
57.6%
Self-reported