# GPT-OSS 120B

OpenAI · Open Weight · rank 181 · bench-align-v5 · Self-hosted

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/models/gpt-oss-120b  
JSON: https://modelchoice.dev/api/model/gpt-oss-120b

## Facts

| Field | Value | Evidence |
| --- | --- | --- |
| Canonical id | `gpt-oss-120b` | — |
| Overall score | 35.4 | Observed 2026-11-21 · source benchlm:models |
| Verified score (BenchLM): a separate BenchLM figure, not the overall score | 54 | Observed 2026-11-21 · source benchlm:models |
| Context window | 128K tokens | Observed 2026-11-21 · source benchlm:models |
| Modalities (models.dev) | Input: text · Output: text | Observed 2026-11-21 · source openrouter:pricing |
| Release date | 2025-08-05 | Observed 2026-11-21 · source benchlm:models |
| Access type | Open Weight | — |
| Blended $/1M (75% input / 25% output) | $0.16 | Derived from the input and output rates below |

## Capability evidence

Seven axes from the ranking source. An axis the source did not score is unavailable, not zero. Beside each score is BenchLM's separate verified score for that axis; the two are published side by side and are not interchangeable.

| Axis | Score | Evidence | Verified (BenchLM) | Verified evidence |
| --- | --- | --- | --- | --- |
| Agentic | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Coding | 47.6 | Observed 2026-11-21 · source benchlm:models | 45.7 | Observed 2026-11-21 · source benchlm:models |
| Knowledge | 32.4 | Observed 2026-11-21 · source benchlm:models | 32.4 | Observed 2026-11-21 · source benchlm:models |
| Reasoning | 59.9 | Observed 2026-11-21 · source benchlm:models | 59.9 | Observed 2026-11-21 · source benchlm:models |
| Multimodal & Grounded | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Instruction Following | 84.1 | Observed 2026-11-21 · source benchlm:models | 84.1 | Observed 2026-11-21 · source benchlm:models |
| Math | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |

## Runtime service evidence

Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim. Regional or per-endpoint measurements appear only when the API supplies them; none are modelled.

| Measurement | Value | Observed | Last good | Evidence |
| --- | --- | --- | --- | --- |
| Time to first token | 9.47 s | 2026-11-21 | 2026-11-21 | Observed 2026-11-21 · source benchlm:speed |
| Throughput | 213 tok/s | 2026-11-21 | 2026-11-21 | Observed 2026-11-21 · source benchlm:speed |

## Endpoint and price matrix

Every published price component, including cache reads and writes.

| Component | USD | Evidence |
| --- | --- | --- |
| Input / 1M tokens | $0.09 | Observed 2026-11-21 · source openrouter:pricing |
| Output / 1M tokens | $0.36 | Observed 2026-11-21 · source openrouter:pricing |
| Cache read / 1M tokens | $0.075 | Last good 2026-11-19 · source openrouter:pricing |
| Cache write / 1M tokens | Unavailable | Unavailable · source openrouter:pricing |
| Blended / 1M (75% input / 25% output) | $0.16 | Derived — from the input and output rates above; it has no source record of its own |
| Cost per successful task (LiveBench) | Unavailable | Unavailable · source livebench:table |
| Batch input / 1M tokens (OpenRouter batch) | $0.0296 | Observed 2026-11-21 · source openrouter:pricing |
| Batch output / 1M tokens (OpenRouter batch) | $0.14 | Observed 2026-11-21 · source openrouter:pricing |

Batch API rate (asynchronous jobs), from OpenRouter's batch listing.

**Self-hosted listing.** Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure. The rates above are a hosted price matched from another provider, not a first-party list price.

## Workload-aware monthly cost example

10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. Derived here from the published rates above by this site's own calculator — not a figure any source published.

| Field | Value |
| --- | --- |
| Modelled monthly cost | $0.44 |
| Modelled tokens | 2.82M |

## Benchmark record

34 matched benchmark rows with their published value, unit, and provenance.

### Knowledge

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AA MMLU-Pro (Artificial Analysis MMLU-Pro) | 80.8 | Professional multi-subject questions | Professional knowledge and reasoning | [Artificial Analysis MMLU-Pro Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/mmlu-pro) |
| MMLU (Massive Multitask Language Understanding) | 90 | 57 subjects | Elementary to professional level | [Measuring Massive Multitask Language Understanding](https://arxiv.org/abs/2009.03300) |
| GPQA (Graduate-Level Google-Proof Q&A) | 80.1 | 448 questions | Graduate level | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |
| HLE (Humanity's Last Exam) | 14.9 | Expert-level questions | Frontier expert level | [Humanity's Last Exam](https://lastexam.ai/) |
| Artificial Analysis Intelligence Index | 3.8 | Cross-benchmark intelligence index | Display-only external reference | [Artificial Analysis](https://artificialanalysis.ai/) |
| AA-GPQA Diamond (Artificial Analysis GPQA Diamond) | 78.2 | Graduate-level science questions | Graduate-level science reasoning | [Artificial Analysis GPQA Diamond Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/gpqa-diamond) |
| AA-HLE (Artificial Analysis Humanity's Last Exam) | 19.6 | Expert-level questions | Frontier expert reasoning | [Artificial Analysis Humanity's Last Exam Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/hle) |
| AA-Omniscience Index (Artificial Analysis Omniscience Index) | -46.4 | Knowledge questions | Broad factual knowledge | [AA-Omniscience: Knowledge and Hallucination Benchmark](https://artificialanalysis.ai/evaluations/omniscience) |
| AA-Omniscience Accuracy (Artificial Analysis Omniscience Accuracy) | 21.7 | Knowledge questions | Broad knowledge | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| AA-Omniscience Hallucination Rate (Artificial Analysis Omniscience Hallucination Rate) | 86.9 | Knowledge questions | Factuality | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |

### Coding

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AA LiveCodeBench (Artificial Analysis LiveCodeBench) | 87.8 | Contamination-resistant coding tasks | Competitive programming | [Artificial Analysis LiveCodeBench Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/livecodebench) |
| SWE-bench Verified (Software Engineering Benchmark Verified) | 62.4 | 500 verified issues | Professional software engineering | [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://arxiv.org/abs/2310.06770) |
| React Native Evals | 71.6 | React Native app implementation tasks | Production mobile app engineering | [React Native Evals](https://rn-evals.vercel.app/) |
| AA Coding Index (Artificial Analysis Coding Index) | 30.4 | Cross-benchmark coding index | Display-only external reference | [Artificial Analysis model leaderboards](https://artificialanalysis.ai/leaderboards/models) |
| AA-SciCode (Artificial Analysis SciCode) | 34.0 | Scientific coding subproblems | Scientific programming | [Artificial Analysis SciCode Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/scicode) |

### Mathematics

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AA AIME 2025 (Artificial Analysis AIME 2025) | 93.4 | 30 AIME 2025 problems | Olympiad mathematics | [Artificial Analysis AIME 2025 Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/aime-2025) |
| AIME 2024 (American Invitational Mathematics Examination 2024) | 95.8 | 15 problems | High school olympiad level | [American Invitational Mathematics Examination](https://www.maa.org/math-competitions/aime) |
| AIME 2025 (American Invitational Mathematics Examination 2025) | 92.5 | 15 problems | High school olympiad level | [American Invitational Mathematics Examination](https://www.maa.org/math-competitions/aime) |

### Reasoning

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AA-LCR (Artificial Analysis Long Context Reasoning) | 52.0 | Long-context reasoning tasks | Long-context reasoning | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| CritPt (Critical Physics Tasks) | 1.1 | Research-level physics questions | Research-level physics reasoning | [CritPt Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/critpt) |

### Instruction Following

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AA-IFBench (Artificial Analysis IFBench) | 69.0 | Verifiable instruction constraints | Instruction precision | [Artificial Analysis IFBench Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/ifbench) |

### Multilingual

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AA Global-MMLU-Lite (Artificial Analysis Global-MMLU-Lite) | 82.8 | Multilingual knowledge questions | Multilingual professional knowledge | [Artificial Analysis Global-MMLU-Lite Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/global-mmlu-lite) |

### Agentic

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AA Harvey LAB v1.0 (Artificial Analysis Harvey LAB-AA v1.0) | 13.9 | Legal agent tasks | Professional legal work | [Artificial Analysis Harvey LAB-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/harvey-lab-aa) |
| AA ITBench (Artificial Analysis ITBench-AA) | 5.6 | IT incident-response tasks | Enterprise IT operations | [Artificial Analysis ITBench-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/itbench-aa) |
| GDPval-AA | 745 | Agentic real-world work tasks | Professional agentic workflows | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| GDPval-AA (GDPval-AA normalized) | 5.4 | Economically valuable tasks | Professional agentic workflows | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| AA Agentic Index (Artificial Analysis Agentic Index) | 6.2 | Cross-benchmark agentic index | Display-only external reference | [Artificial Analysis model leaderboards](https://artificialanalysis.ai/leaderboards/models) |
| APEX-Agents-AA | 3.1 | 452 professional-services agent tasks | Long-horizon workplace agent tasks | [APEX-Agents-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/apex-agents-aa) |
| Gert Labs (Gert Labs Composite Game Benchmark) | 29.61 | Novel game environments | Agentic coding and decision-making | [Gert Labs rankings](https://gertlabs.com/rankings) |
| τ²-bench results (τ²-Bench Tool-Agent-User Evaluation) | 65.8 | Airline, retail, and telecom customer-service task sets | Dual-control customer-service workflows | [τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://arxiv.org/abs/2506.07982) |

### Multimodal & Grounded

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Design Arena Website (Design Arena Website Elo) | 955 | Website generation comparisons | Design and website generation | [OpenRouter Grok 4.3 benchmarks](https://openrouter.ai/x-ai/grok-4.3/benchmarks) |

### external

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Mystery Game Puzzles (Mystery Game Puzzles (Epoch AI)) | 0.0 | 100 single-best-move positions from an undisclosed game | Unfamiliar game positions, single best move | [Mystery Game Puzzles (Epoch AI)](https://epoch.ai/benchmarks/mystery-game-puzzles) |
| FailureSensorIQ | 50.5 | Multiple-choice questions on sensors and failure modes for 10 industrial assets | Industrial maintenance and reliability knowledge | [BenchLM](https://benchlm.ai/benchmarks/failuresensoriq) |
| CompileBench (CompileBench (building real projects from source, pass@1)) | 42.2 | 15 build tasks on cowsay, jq, GNU coreutils and curl, three attempts each (45 attempts) | Dependency resolution, legacy toolchains, static linking and cross-compilation | [CompileBench: can AI compile 22-year-old code? (Quesma)](https://quesma.com/blog/introducing-compilebench/) |

## Independent scores (Epoch AI)

A second, independent score source: Epoch's own figures in Epoch's units, one line per model version Epoch evaluated (effort setting as Epoch labels it); higher is better. Not part of this site's capability scores or rank.

| Benchmark | Variant | Score | Unit | Epoch date | Evidence |
| --- | --- | --- | --- | --- | --- |
| Terminal-Bench | default (Terminus 2 (best of 2 agents)) | 0.187 | fraction (0–1) | 2025-11-01 | Observed 2026-11-21 · source epoch:benchmarks |
| Terminal-Bench | unknown (Terminus 2 (best of 2 agents)) | 0.1869 | fraction (0–1) | 2025-08-05 | Observed 2026-11-21 · source epoch:benchmarks |
| Aider polyglot | high (diff) | 41.8% | percent | — | Observed 2026-11-21 · source epoch:benchmarks |
| METR time horizon | default (METR version not stated) | 42 min | minutes | — | Observed 2026-11-21 · source epoch:benchmarks |

Source: [Epoch AI, CC BY 4.0](https://epoch.ai/benchmarks) ([licence](https://creativecommons.org/licenses/by/4.0/)). Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from https://epoch.ai/benchmarks.

## Lifecycle and limitations log

Lifecycle events the source associates with this model.

No lifecycle event references this model. That is not evidence the model has no lifecycle plan — only that this source published none.

## What this profile does not claim

Values are reproduced exactly as their sources published them, in the units those sources declared; none are converted, interpolated, or averaged across providers. Any field marked unavailable was attempted and not returned. Last attempted fetch for this model's score: 2026-11-21 05:17 UTC.
