# GPT-5.2

OpenAI · Proprietary · rank 56 · bench-align-v5

> 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://modelscale.dev/models/gpt-5-2  
JSON: https://modelscale.dev/api/model/gpt-5-2

## Facts

| Field | Value | Evidence |
| --- | --- | --- |
| Canonical id | `gpt-5-2` | — |
| Overall score | 60.1 | Observed 2026-11-21 · source benchlm:models |
| Verified score (BenchLM): a separate BenchLM figure, not the overall score | 59 | Observed 2026-11-21 · source benchlm:models |
| Context window | 400K tokens | Observed 2026-11-21 · source benchlm:models |
| Max output (models.dev) | 128,000 tokens | Observed 2026-11-21 · source modelsdev:catalog |
| Modalities (models.dev) | Input: text, image · Output: text | Observed 2026-11-21 · source modelsdev:catalog |
| Release date | 2025-12-11 | Observed 2026-11-21 · source benchlm:models |
| Access type | Proprietary | — |
| Blended $/1M (75% input / 25% output) | $4.81 | 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 | 27.1 | Observed 2026-11-21 · source benchlm:models | 26.5 | Observed 2026-11-21 · source benchlm:models |
| Coding | 57.9 | Observed 2026-11-21 · source benchlm:models | 57.4 | Observed 2026-11-21 · source benchlm:models |
| Knowledge | 72.9 | Observed 2026-11-21 · source benchlm:models | 73 | Observed 2026-11-21 · source benchlm:models |
| Reasoning | 62.1 | Observed 2026-11-21 · source benchlm:models | 62.1 | Observed 2026-11-21 · source benchlm:models |
| Multimodal & Grounded | 74.8 | Observed 2026-11-21 · source benchlm:models | 74.8 | Observed 2026-11-21 · source benchlm:models |
| Instruction Following | 92.4 | Observed 2026-11-21 · source benchlm:models | 92.4 | Observed 2026-11-21 · source benchlm:models |
| Math | 65.3 | Observed 2026-11-21 · source benchlm:models | 65.3 | Observed 2026-11-21 · 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 | 81.31 s | 2026-11-21 | 2026-11-21 | Observed 2026-11-21 · source benchlm:speed |
| Throughput | 80 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 | $1.75 | Observed 2026-11-21 · source benchlm:pricing |
| Output / 1M tokens | $14.00 | Observed 2026-11-21 · source benchlm:pricing |
| Cache read / 1M tokens | Unavailable | Unavailable · source benchlm:pricing |
| Cache write / 1M tokens | Unavailable | Unavailable · source openrouter:pricing |
| Blended / 1M (75% input / 25% output) | $4.81 | 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 |

**Pricing note.** OpenAI's GPT-5.2 model page lists GPT-5.2 at $1.75 input / $14.00 output per million tokens.

## 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 | $13.55 |
| Modelled tokens | 2.82M |

## Benchmark record

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

### Knowledge

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AA MMLU-Pro (Artificial Analysis MMLU-Pro) | 87.4 | Professional multi-subject questions | Professional knowledge and reasoning | [Artificial Analysis MMLU-Pro Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/mmlu-pro) |
| GPQA (Graduate-Level Google-Proof Q&A) | 92.4 | 448 questions | Graduate level | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |
| Artificial Analysis Intelligence Index | 30.4 | Cross-benchmark intelligence index | Display-only external reference | [Artificial Analysis](https://artificialanalysis.ai/) |
| AA-GPQA Diamond (Artificial Analysis GPQA Diamond) | 90.3 | 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) | 37.7 | 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) | -0.9 | Knowledge questions | Broad factual knowledge | [AA-Omniscience: Knowledge and Hallucination Benchmark](https://artificialanalysis.ai/evaluations/omniscience) |
| AA-Omniscience Accuracy (Artificial Analysis Omniscience Accuracy) | 44.3 | Knowledge questions | Broad knowledge | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| AA-Omniscience Hallucination Rate (Artificial Analysis Omniscience Hallucination Rate) | 81.2 | Knowledge questions | Factuality | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| GPQA Diamond (Vals) (GPQA Diamond, Vals AI run) | 91.7 | Graduate-level science questions | Expert reasoning | [Vals AI GPQA Diamond, Vals AI run leaderboard](https://www.vals.ai/benchmarks/gpqa) |
| MMLU-Pro (Vals) (MMLU-Pro, Vals AI run) | 86.2 | Academic multiple-choice questions | Broad academic knowledge | [Vals AI MMLU-Pro, Vals AI run leaderboard](https://www.vals.ai/benchmarks/mmlu_pro) |

### Coding

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| SWE-bench Verified (Software Engineering Benchmark Verified) | 80 | 500 verified issues | Professional software engineering | [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://arxiv.org/abs/2310.06770) |
| SWE-bench Pro | 55.6 | 1,865 repository problems | Long-horizon professional engineering | [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://arxiv.org/abs/2509.16941) |
| Vibe Code Bench (Vibe Code Bench v1.1) | 53.50 | End-to-end web application builds | End-to-end software delivery | [Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development](https://www.vals.ai/benchmarks/vibe-code) |
| LiveCodeBench (Vals) (LiveCodeBench, Vals AI run) | 85.4 | Competitive programming problems (easy, medium, hard) | Frontier coding | [Vals AI LiveCodeBench, Vals AI run leaderboard](https://www.vals.ai/benchmarks/lcb) |
| SWE-bench (Vals) (SWE-bench, Vals AI run) | 75.8 | Real repository issues by human time bucket | Frontier coding agents | [Vals AI SWE-bench, Vals AI run leaderboard](https://www.vals.ai/benchmarks/swebench) |
| PostTrainBench v1 (PostTrainBench v1 (archived)) | 21.4 | Post-training four base models on seven benchmarks | Autonomous ML engineering | [PostTrainBench v1 leaderboard (archived)](https://posttrainbench.com/?version=v1) |

### Mathematics

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AA AIME 2025 (Artificial Analysis AIME 2025) | 99.0 | 30 AIME 2025 problems | Olympiad mathematics | [Artificial Analysis AIME 2025 Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/aime-2025) |
| AIME 2025 (American Invitational Mathematics Examination 2025) | 100 | 15 problems | High school olympiad level | [American Invitational Mathematics Examination](https://www.maa.org/math-competitions/aime) |
| FrontierMath v2 (Tiers 1-3) (FrontierMath v2 Tiers 1-3) | 67.400 | 285 private advanced mathematics problems | From olympiad-plus to early research mathematics | [FrontierMath v2 benchmark hub](https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2) |
| FrontierMath v2 (Tier 4) (FrontierMath v2 Tier 4) | 31.700 | 41 private extreme-difficulty mathematics problems | Research-level mathematics requiring hours or days of expert work | [FrontierMath Tier 4 v2 leaderboard](https://epoch.ai/benchmarks/frontiermath-tier-4-v2?view=graph&tab=leaderboard) |

### Reasoning

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| ARC-AGI-1 (ARC-AGI-1 Semi-Private Evaluation) | 86.17 | Semi-private ARC-AGI-1 evaluation set | Abstract visual reasoning | [ARC Prize leaderboard](https://arcprize.org/) |
| ARC-AGI-2 (Abstraction and Reasoning Corpus for AGI v2) | 52.9 | Visual pattern completion and abstract reasoning | Expert-level — hardest public reasoning benchmark | [ARC-AGI-2: A Harder General Intelligence Benchmark](https://arcprize.org/arc-agi/2/) |
| AA-LCR (Artificial Analysis Long Context Reasoning) | 82.7 | Long-context reasoning tasks | Long-context reasoning | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| CritPt (Critical Physics Tasks) | 11.6 | Research-level physics questions | Research-level physics reasoning | [CritPt Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/critpt) |
| BioBasicsBench (BioBasicsBench: everyday wet-lab science) | 31.2 | 100 routine wet-lab analysis tasks (88 multimodal) across five domains | Routine wet-lab data interpretation | [Measuring how AI agents handle everyday wet-lab science](https://openai.com/index/measuring-how-ai-agents-handle-wet-lab-science/) |

### Instruction Following

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AA-IFBench (Artificial Analysis IFBench) | 75.4 | Verifiable instruction constraints | Instruction precision | [Artificial Analysis IFBench Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/ifbench) |

### Agentic

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| BrowseComp | 65.8 | Research questions requiring browsing | Hard web research | [BrowseComp](https://openai.com/index/browsecomp/) |
| Gert Labs (Gert Labs Composite Game Benchmark) | 46.54 | Novel game environments | Agentic coding and decision-making | [Gert Labs rankings](https://gertlabs.com/rankings) |
| OSWorld-Verified | 47.3 | 369 real-world computer tasks (361 when eight Google Drive tasks are excluded) | Multi-step desktop and cross-application workflows | [OSWorld](https://os-world.github.io/) |
| JobBench | 34.3 | 130 tasks across 35 occupations | Professional multi-source workflows | [JobBench: Aligning Agent Work With Human Will](https://arxiv.org/abs/2605.26329) |
| τ²-bench results (τ²-Bench Tool-Agent-User Evaluation) | 84.8 | 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) |
| LifeVal (LifeVal: everyday life tasks) | 49.3 | 169 everyday life tasks (caregiving, health, education, household administration, personal finance, shopping, government services) | Agentic personal-assistant work | [LifeVal](https://openai.com/index/lifeval/) |

### Multimodal & Grounded

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| MMMU (Massive Multi-discipline Multimodal Understanding) | 86.7 | Multimodal academic reasoning | Frontier multimodal | [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://arxiv.org/abs/2401.05508) |
| MMMU-Pro (Massive Multi-discipline Multimodal Understanding Pro) | 79.5 | Multimodal academic reasoning | Frontier multimodal | [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://arxiv.org/abs/2409.02813) |
| Design Arena Website (Design Arena Website Elo) | 1183 | Website generation comparisons | Design and website generation | [OpenRouter Grok 4.3 benchmarks](https://openrouter.ai/x-ai/grok-4.3/benchmarks) |
| OmniDocBench 1.5 | 85.7 | Document understanding tasks | Grounded document reasoning | [Introducing GPT-5.4 mini and nano](https://openai.com/index/introducing-gpt-5-4-mini-and-nano/) |
| RealWorldQA | 83.3 | Real-world visual question answering | General visual reasoning | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |
| Video-MME (with subtitle) (Video-MME with subtitle) | 86.0 | Video understanding | Multimodal video reasoning | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |
| Video-MME (w/o subtitle) (Video-MME without subtitle) | 85.8 | Video understanding | Multimodal video reasoning | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |
| MathVision | 83.0 | Visually grounded math problems | Advanced multimodal mathematics | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |
| We-Math | 79.0 | Visually grounded math problems | Advanced multimodal mathematics | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |
| DynaMath | 86.8 | Dynamic visual math problems | Advanced multimodal mathematics | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |
| CC-OCR | 70.3 | Optical character recognition | Document reading | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |
| AI2D_TEST (AI2D test split) | 92.2 | Diagram understanding | Structured visual reasoning | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |
| CountBench | 91.9 | Visual counting tasks | Fine-grained visual perception | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |
| ERQA | 59.8 | Evidence-based visual QA | Grounded multimodal reasoning | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |
| VideoMMMU | 85.9 | Video-grounded expert reasoning | Frontier multimodal video reasoning | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |
| MLVU (M-Avg) (MLVU mean average) | 85.6 | General video understanding | Broad multimodal video reasoning | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |
| SimpleVQA | 55.8 | Visual QA tasks | General visual understanding | [GLM-5V-Turbo](https://docs.z.ai/guides/vlm/glm-5v-turbo) |
| V* | 75.9 | Frontier multimodal reasoning tasks | Frontier multimodal | [GLM-5V-Turbo](https://docs.z.ai/guides/vlm/glm-5v-turbo) |
| CharXiv (CharXiv Reasoning) | 82.1 | Scientific chart reasoning | Scientific visualization reasoning | [CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs](https://charxiv.github.io/) |

### external

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Chess Puzzles (Chess Puzzles (Epoch AI)) | 48.0 | 100 programmatically generated chess positions with a single best move | Novel chess positions, single best move | [Chess Puzzles (Epoch AI)](https://epoch.ai/benchmarks/chess-puzzles) |
| Mystery Game Puzzles (Mystery Game Puzzles (Epoch AI)) | 23.0 | 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) |
| Furniture Assembly (Furniture Assembly Benchmark (Epoch AI)) | 38.3 | 60 photos of three IKEA builds, some with deliberate assembly mistakes | Spatial reasoning from technical diagrams to real photos | [Furniture Assembly Benchmark (Epoch AI)](https://epoch.ai/benchmarks/furniture-assembly) |
| EBR-bench (Earthborne Rangers (EBR-bench)) | 23.0 | Ten playthroughs of an Earthborne Rangers campaign segment per sample (eight learning, two scored) | Learning an unfamiliar game over multi-hour playthroughs | [Earthborne Rangers (EBR-bench), Epoch AI](https://epoch.ai/benchmarks/ebr-bench) |
| MirrorCode (MirrorCode (Epoch AI and METR)) | 32.2 | 30 reimplementation tasks (15 programs in two languages), three attempts each | Days-long software engineering without source code | [MirrorCode (Epoch AI)](https://epoch.ai/benchmarks/mirrorcode) |
| Game Arena Go | 561 | Head-to-head Go games on a 13 x 13 board | Strategic planning and rule-following | [BenchLM](https://benchlm.ai/benchmarks/game-arena-go) |
| BinaryAudit (BinaryAudit (backdoor detection in compiled binaries)) | 17.5 | 19 backdoor and timebomb detection tasks on stripped binaries, three runs each (57 runs); 6 tooling and 8 clean-binary tasks reported alongside | Reverse engineering without source code or symbols | [We hid backdoors in ~40 MB binaries and asked AI + Ghidra to find them (Quesma)](https://quesma.com/blog/introducing-binaryaudit/) |
| OTelBench (OTelBench (OpenTelemetry instrumentation tasks)) | 26.1 | 23 OpenTelemetry instrumentation tasks in 11 languages, three attempts each (69 runs) | Distributed tracing and context propagation across services | [Benchmarking OpenTelemetry: can AI trace your failed login? (Quesma)](https://quesma.com/blog/introducing-otel-bench/) |
| NYT Connections (NYT Connections LLM Benchmark (extended version)) | 83.6 | 940 NYT Connections puzzles, each with up to four added trick words | Wordplay, word knowledge and decoys that fit almost-but-not-quite | [NYT Connections LLM Benchmark (Lech Mazur, GitHub)](https://github.com/lechmazur/nyt-connections) |
| SkillsBench official leaderboard (BenchFlow) (SkillsBench v1.1 official leaderboard (BenchFlow)) | 51.7 | 87 tasks in 8 domains (SkillsBench v1.1) | Multi-step agent tasks | [SkillsBench leaderboard](https://www.skillsbench.ai/leaderboard) |

## 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 01:17 UTC.
