OpenAI, open weights

# gpt-oss-120b

> gpt-oss-120b by OpenAI, released August 2025. Ranked #217 of 354 with a Noometry Index of 36.3. API: $0.037 in / $0.17 out per M tokens. 131K context. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/gpt-oss-120b
- Last updated: 2026-10-10
- Title: gpt-oss-120b Benchmarks, Price & Rank (October 2026)

gpt-oss-120b by OpenAI ranks 217th of 354 ranked models on the Noometry Index as of October 2026, with a score of 36.3. Its strongest category is math, where it ranks 50th. API pricing starts at $0.037 per million input tokens and $0.17 per million output tokens, with a 131K-token context window.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #217 of 354
- **Index score:** 36.3
- **Evidence:** Confirmed 48 results
- **Provider:** [OpenAI](https://noometry.com/providers/openai)
- **Released:** August 5, 2025
- **Weights:** Open weights
- **Reasoning:** Yes
- **Context window:** 131K
- **Max output:** 41K
- **Input price:** $0.037 / M
- **Output price:** $0.17 / M
- **Blended price:** $0.0703 / M
- **Output speed:** 55 tokens/s [Kagi](https://help.kagi.com/kagi/ai/llm-benchmark.html)
- **Value:** #6 of 219
- **Knowledge cutoff:** August 2025
- **Input:** text
- **Hugging Face:** [openai/gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b)

## Category scores

Each category score combines every public result we have in that category.

gpt-oss-120b category scores

1.  Coding 33.5
2.  Agentic & Tool Use 12.2
3.  Reasoning 20.0
4.  Math 52.5
5.  Knowledge 42.4
6.  Multilingual 48.0
7.  Instruction Following 69.3
8.  Long Context 31.4
9.  Writing & Preference 46.5
10.  020406080

gpt-oss-120b category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 33.5 | #256 | 5 |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 12.2 | #153 | 2 |
| [Reasoning](https://noometry.com/best/reasoning) | 20.0 | #245 | 9 |
| [Math](https://noometry.com/best/math) | 52.5 | #50 | 3 |
| [Knowledge](https://noometry.com/best/knowledge) | 42.4 | #96 | 6 |
| [Multilingual](https://noometry.com/best/multilingual) | 48.0 | #147 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 69.3 | #173 | 2 |
| [Long Context](https://noometry.com/best/long-context) | 31.4 | #278 | 2 |
| [Writing & Preference](https://noometry.com/best/writing) | 46.5 | #217 | 6 |

## Strengths and weaknesses

Categories where gpt-oss-120b places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

gpt-oss-120b: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Math](https://noometry.com/best/math) | 52.5 | +15.9 | #50 of 327, top 16% |
| [Knowledge](https://noometry.com/best/knowledge) | 42.4 | +5.0 | #96 of 314, top 31% |
| [Multilingual](https://noometry.com/best/multilingual) | 48.0 | +0.6 | #147 of 297, top 50% |

### Weakest categories

gpt-oss-120b: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 12.2 | −18.2 | #153 of 154, top 100% |
| [Long Context](https://noometry.com/best/long-context) | 31.4 | −9.5 | #278 of 296, top 94% |
| [Coding](https://noometry.com/best/coding) | 33.5 | −5.3 | #256 of 340, top 76% |

## Closest competitors

The models ranked just above and below gpt-oss-120b. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to gpt-oss-120b
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [Llama 3.1 Nemotron Ultra 253b v1](https://noometry.com/models/llama-3-1-nemotron-ultra-253b-v1) | #213 | 36.7 | — | — | [Compare](https://noometry.com/compare/gpt-oss-120b-vs-llama-3-1-nemotron-ultra-253b-v1) |
| [Granite 4.0 H Small](https://noometry.com/models/ibm-granite-h-small) | #214 | 36.5 | — | — | [Compare](https://noometry.com/compare/gpt-oss-120b-vs-ibm-granite-h-small) |
| [Command A](https://noometry.com/models/command-a) | #215 | 36.5 | $4.38 | 28 | [Compare](https://noometry.com/compare/command-a-vs-gpt-oss-120b) |
| [Grok Build 0.1](https://noometry.com/models/grok-build-0-1) | #216 | 36.4 | $1.25 | — | [Compare](https://noometry.com/compare/gpt-oss-120b-vs-grok-build-0-1) |
| [Mistral Medium](https://noometry.com/models/mistral-medium) | #218 | 36.3 | $3 | 68 | [Compare](https://noometry.com/compare/gpt-oss-120b-vs-mistral-medium) |
| [GPT-4.1](https://noometry.com/models/gpt-4-1) | #219 | 35.9 | $3.50 | 116 | [Compare](https://noometry.com/compare/gpt-4-1-vs-gpt-oss-120b) |
| [Deepseek Coder v2](https://noometry.com/models/deepseek-coder-v2) | #220 | 35.9 | — | — | [Compare](https://noometry.com/compare/deepseek-coder-v2-vs-gpt-oss-120b) |
| [C4ai Aya Expanse 32b](https://noometry.com/models/c4ai-aya-expanse-32b) | #221 | 35.9 | — | — | [Compare](https://noometry.com/compare/c4ai-aya-expanse-32b-vs-gpt-oss-120b) |

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

### Coding

gpt-oss-120b Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [SWE-bench Verified (bash only)](https://noometry.com/benchmarks/swe-bench-bash-only) | 26% | #33 of 39, top 85% |  | [SWE-bench](https://www.swebench.com/) | 2025-08-07 |
| [Aider Polyglot](https://noometry.com/benchmarks/aider-polyglot) | 41.8% | #26 of 44, top 60% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Aider Polyglot](https://noometry.com/benchmarks/aider-polyglot) | 41.8% | #26 of 44, top 60% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SciCode](https://noometry.com/benchmarks/scicode) | 34% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SciCode](https://noometry.com/benchmarks/scicode) | 36% | #93 of 121, top 77% | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 48.2% | #51 of 119, top 43% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 48.2% | #51 of 119, top 43% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 41.9% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1380 | #150 of 294, top 52% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [ALE-Bench](https://noometry.com/benchmarks/ale-bench) | 575.62 | #82 of 105, top 79% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [AlgoTune](https://noometry.com/benchmarks/algotune) | 1.41 | #14 of 18, top 78% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Agentic & Tool Use

gpt-oss-120b Agentic & Tool Use benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Terminal-Bench](https://noometry.com/benchmarks/terminal-bench) | 18.7% | #38 of 41, top 93% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [APEX-Agents](https://noometry.com/benchmarks/apex-agents) | 4.4% | #49 of 49, top 100% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [METR Time Horizons](https://noometry.com/benchmarks/metr-time-horizons) | 56.6% | #20 of 32, top 63% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Vending-Bench 2](https://noometry.com/benchmarks/vending-bench-2) | \-21.53 | #58 of 60, top 97% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Reasoning

gpt-oss-120b Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [SimpleBench](https://noometry.com/benchmarks/simplebench) | 22.1% | #72 of 77, top 94% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Kagi LLM Benchmark](https://noometry.com/benchmarks/kagi-reasoning) | 58.6% | #43 of 99, top 44% |  | [Kagi LLM Benchmark](https://help.kagi.com/kagi/ai/llm-benchmark.html) |  |
| [CritPt](https://noometry.com/benchmarks/critpt) | 1.1% | #81 of 134, top 61% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CritPt](https://noometry.com/benchmarks/critpt) | 0% |  | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 20% | #58 of 129, top 45% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1364 | #151 of 297, top 51% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles) | 0% |  | high | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles) | 2% | #74 of 74, top 100% | medium | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 76.3% | #85 of 151, top 57% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMCA](https://noometry.com/benchmarks/lmca) | 22.1% | #91 of 125, top 73% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Surface Evolver Bench](https://noometry.com/benchmarks/surface-evolver-bench) | 25% | #23 of 25, top 92% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 139.93 | #108 of 213, top 51% |  | [Epoch AI](https://epoch.ai/eci) | 2025-08-05 |

### Math

gpt-oss-120b Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 88.9% | #55 of 173, top 32% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [Omni-MATH](https://noometry.com/benchmarks/omni-math) | 68.8% | #5 of 57, top 9% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1389 | #138 of 285, top 49% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Knowledge

gpt-oss-120b Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 75.8% | #92 of 186, top 50% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [MMLU-Pro](https://noometry.com/benchmarks/mmlu-pro) | 79.5% | #17 of 58, top 30% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [Confabulations](https://noometry.com/benchmarks/confabulations) (lower is better) | 15.7% | #21 of 51, top 42% | medium reasoning | [Lech Mazur benchmarks](https://github.com/lechmazur/confabulations) |  |
| [Vectara Hallucination Rate](https://noometry.com/benchmarks/vectara-hallucination) (lower is better) | 14.2% | #83 of 96, top 87% |  | [Vectara Hallucination Leaderboard](https://github.com/vectara/hallucination-leaderboard) |  |
| [GPQA (HELM)](https://noometry.com/benchmarks/helm-gpqa) | 68.4% | #12 of 57, top 22% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1356 | #152 of 273, top 56% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Multilingual

gpt-oss-120b Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1351 | #147 of 297, top 50% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1385 | #147 of 285, top 52% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1369 | #136 of 223, top 61% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1353 | #128 of 231, top 56% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1331 | #109 of 211, top 52% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1282 | #138 of 213, top 65% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1343 | #149 of 283, top 53% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1389 | #121 of 226, top 54% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

gpt-oss-120b Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [IFEval](https://noometry.com/benchmarks/ifeval) | 83.6% | #27 of 57, top 48% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1318 | #164 of 298, top 56% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

gpt-oss-120b Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Fiction.LiveBench](https://noometry.com/benchmarks/fiction-livebench) | 36.1% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Fiction.LiveBench](https://noometry.com/benchmarks/fiction-livebench) | 44.4% | #41 of 47, top 88% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1319 | #173 of 291, top 60% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

gpt-oss-120b Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1365 | #147 of 297, top 50% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1275 | #187 of 295, top 64% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [Short-Story Creative Writing](https://noometry.com/benchmarks/lech-mazur-writing) | 77.1% | #18 of 39, top 47% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [EQ-Bench Creative Writing](https://noometry.com/benchmarks/eqbench-creative-writing) | 961 | #97 of 115, top 85% |  | [EQ-Bench](https://eqbench.com/creative_writing.html) |  |
| [WildBench](https://noometry.com/benchmarks/wildbench) | 84.5% | #14 of 57, top 25% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1340 | #162 of 295, top 55% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## API pricing by provider

gpt-oss-120b API prices
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
| --- | --- | --- | --- | --- |
| [bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) | $0.15 | $0.60 | — | 2026-10-10 |
| [cerebras](https://inference-docs.cerebras.ai/models/overview) | $0.35 | $0.75 | — | 2026-10-10 |
| [deepinfra](https://deepinfra.com/models) | $0.037 | $0.17 | — | 2026-10-10 |
| [fireworks](https://fireworks.ai/docs/) | $0.15 | $0.60 | $0.015 | 2026-10-10 |
| [groq](https://console.groq.com/docs/models) | $0.15 | $0.60 | $0.075 | 2026-10-10 |
| [openrouter](https://openrouter.ai/openai/gpt-oss-120b) | $0.037 | $0.17 | — | 2026-10-10 |
| [together](https://docs.together.ai/docs/serverless-models) | $0.15 | $0.60 | — | 2026-10-10 |
| [vertex](https://cloud.google.com/vertex-ai/generative-ai/docs/models) | $0.09 | $0.36 | — | 2026-10-10 |

[All OpenAI API prices →](https://noometry.com/llm-pricing/openai) [Estimate your cost →](https://noometry.com/tools/cost-calculator)

## Compare gpt-oss-120b

-   [gpt-oss-120b vs Grok Build 0.1](https://noometry.com/compare/gpt-oss-120b-vs-grok-build-0-1)
-   [gpt-oss-120b vs Mistral Medium](https://noometry.com/compare/gpt-oss-120b-vs-mistral-medium)
-   [gpt-oss-120b vs Command A](https://noometry.com/compare/command-a-vs-gpt-oss-120b)
-   [gpt-oss-120b vs GPT-4.1](https://noometry.com/compare/gpt-4-1-vs-gpt-oss-120b)
-   [gpt-oss-120b vs Granite 4.0 H Small](https://noometry.com/compare/gpt-oss-120b-vs-ibm-granite-h-small)
-   [gpt-oss-120b vs Deepseek Coder v2](https://noometry.com/compare/deepseek-coder-v2-vs-gpt-oss-120b)
-   [gpt-oss-120b vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-gpt-oss-120b)
-   [gpt-oss-120b vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-gpt-oss-120b)
-   [gpt-oss-120b vs Kimi K3](https://noometry.com/compare/gpt-oss-120b-vs-kimi-k3)
-   [gpt-oss-120b vs Grok 4.6](https://noometry.com/compare/gpt-oss-120b-vs-grok-4-6)
-   [gpt-oss-120b vs Qwen3.8 Max](https://noometry.com/compare/gpt-oss-120b-vs-qwen3-8-max)
-   [gpt-oss-120b vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-gpt-oss-120b)
-   [gpt-oss-120b vs Muse Spark 1.3](https://noometry.com/compare/gpt-oss-120b-vs-muse-spark-1-3)
-   [gpt-oss-120b vs DeepSeek V4 Pro](https://noometry.com/compare/deepseek-v4-pro-vs-gpt-oss-120b)

## Other OpenAI models

-   [GPT-6 Astra](https://noometry.com/models/gpt-6-astra)70.8
-   [GPT-6.1 Sol](https://noometry.com/models/gpt-6-1-sol)65.6
-   [GPT-5.6 Sol](https://noometry.com/models/gpt-5-6-sol)65.0
-   [GPT-5.5 Pro](https://noometry.com/models/gpt-5-5-pro)64.3
-   [GPT-5.5](https://noometry.com/models/gpt-5-5)63.4
-   [GPT-6 Sol](https://noometry.com/models/gpt-6-sol)61.8
-   [GPT-5.4](https://noometry.com/models/gpt-5-4)59.4
-   [GPT-5.6 Terra](https://noometry.com/models/gpt-5-6-terra)59.2

## Frequently asked questions

### How good is gpt-oss-120b?

gpt-oss-120b by OpenAI ranks 217th of 354 ranked models on the Noometry Index as of October 2026, with a score of 36.3. Its strongest category is math, where it ranks 50th. API pricing starts at $0.037 per million input tokens and $0.17 per million output tokens, with a 131K-token context window.

### How much does gpt-oss-120b cost?

gpt-oss-120b costs $0.037 per million input tokens and $0.17 per million output tokens on deepinfra.

### What is gpt-oss-120b's context window?

gpt-oss-120b accepts up to 131K tokens of input and can write up to 41K tokens in one response.

### Is gpt-oss-120b open source?

Yes. gpt-oss-120b's weights are downloadable from Hugging Face (openai/gpt-oss-120b); check the license for commercial terms.

### How fast is gpt-oss-120b?

gpt-oss-120b generated about 55 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.

### What are gpt-oss-120b's strengths and weaknesses?

Relative to other ranked models, gpt-oss-120b places best in math, knowledge, multilingual and lowest in agentic & tool use, long context, coding.

### What is gpt-oss-120b best at?

Its best category is math, where it ranks 50th on Noometry.

### Cite this page

Noometry. (2026). gpt-oss-120b benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/gpt-oss-120b

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/gpt-oss-120b.md).