# LongCat-2.5

Meituan · Open Weight · 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/longcat-2-5  
JSON: https://modelscale.dev/api/model/longcat-2-5

## Facts

| Field | Value | Evidence |
| --- | --- | --- |
| Canonical id | `longcat-2-5` | — |
| Overall score | Unavailable | Unavailable · source benchlm:models |
| Verified score (BenchLM): a separate BenchLM figure, not the overall score | 77 | Observed 2026-11-21 · source benchlm:models |
| Context window | 1M tokens | Observed 2026-11-21 · source benchlm:models |
| Release date | 2026-11-02 | Observed 2026-11-21 · source benchlm:models |
| Access type | Open Weight | — |
| Blended $/1M (75% input / 25% output) | $0.52 | Derived from the input and output rates below |

**Only a verified score is published.** BenchLM publishes no overall score for this model, so the overall score stays unavailable. The verified score beside it is a separate figure in BenchLM's data. BenchLM does not document how the two are calculated differently, and they can differ widely, so one is never used in place of the other.

## 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 | 84.3 | Observed 2026-11-21 · source benchlm:models |
| Coding | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Knowledge | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Reasoning | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Multimodal & Grounded | Unavailable | Unavailable · source benchlm:models | 82.7 | Observed 2026-11-21 · source benchlm:models |
| Instruction Following | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · 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 | Unavailable | Unavailable | Unavailable | Unavailable · source benchlm:speed |
| Throughput | Unavailable | Unavailable | Unavailable | Unavailable · source benchlm:speed |

## Endpoint and price matrix

Every published price component, including cache reads and writes.

| Component | USD | Evidence |
| --- | --- | --- |
| Input / 1M tokens | $0.30 | Observed 2026-11-21 · source benchlm:pricing |
| Output / 1M tokens | $1.20 | Observed 2026-11-21 · source benchlm:pricing |
| Cache read / 1M tokens | $0.006 | Observed 2026-11-21 · source benchlm:pricing |
| Cache write / 1M tokens | Unavailable | Unavailable · source openrouter:pricing |
| Blended / 1M (75% input / 25% output) | $0.52 | 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.** The LongCat API Platform added LongCat-2.5 on November 2, 2026 and lists it as the only pay-as-you-go model at a limited-time discounted price of $0.30 uncached input, $0.006 cached input and $1.20 output per million tokens. Meituan has not published a standard (non-discount) rate for LongCat-2.5; LongCat-2.0's standard rate was $0.75 / $2.95. Token Packs bill cache hits as free. The MIT weights are also self-hostable.

## 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 | $1.48 |
| Modelled tokens | 2.82M |

## Benchmark record

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

### Knowledge

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| FrontierScience | 77 | Research-level science tasks | Research frontier | [FrontierScience](https://openai.com/index/frontierscience/) |

### Coding

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Terminal-Bench 2.1 | 88.4 | Terminal-based software-agent tasks | Professional software engineering | [Terminal-Bench](https://www.tbench.ai/) |
| ProgramBench (ProgramBench: Can Language Models Rebuild Programs From Scratch?) | 25.5 | 200 program reconstruction tasks | Full-repository software architecture | [ProgramBench: Can Language Models Rebuild Programs From Scratch?](https://programbench.com/static/paper.pdf) |
| SWE-Atlas Codebase QnA | 58.3 | 124 codebase questions across 11 repositories | Production codebase comprehension | [Muse Spark 1.3 Evaluation Methodology](https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology) |
| PaperBench | 82.1 | AI research-paper reproduction | Frontier autonomous research and engineering | [Qwen3.8-Max: A New Bar for Coding and Cowork](https://qwen.ai/blog?id=qwen3.8) |
| NL2Repo | 60.5 | Natural language to repository tasks | System-level software comprehension | [MiniMax M2.7: Early Echoes of Self-Evolution](https://www.minimax.io/news/minimax-m27-en) |
| DeepSWE | 64.6 | 113 software engineering tasks across 91 repositories and 5 languages | Long-horizon software engineering | [DeepSWE benchmark blog](https://deepswe.datacurve.ai/blog) |

### Agentic

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Terminal-Bench 4.0 | 38.50 | 66 professional computer-work tasks | Frontier autonomous knowledge work | [Terminal-Bench 4.0](https://www.tbench.ai/news/terminal-bench-4-0) |
| Terminal-Bench 2.1 | 88.4 | Terminal-based software-agent tasks | Professional software engineering | [Terminal-Bench](https://www.tbench.ai/) |
| BrowseComp | 91.9 | Research questions requiring browsing | Hard web research | [BrowseComp](https://openai.com/index/browsecomp/) |
| HLE w/ tools (Humanity's Last Exam with tools) | 63.1 | Expert questions with tool use | Frontier tool-augmented reasoning | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| JobBench | 65.4 | 130 tasks across 35 occupations | Professional multi-source workflows | [JobBench: Aligning Agent Work With Human Will](https://arxiv.org/abs/2605.26329) |
| MCP Atlas | 83.1 | Tool-integrated agent tasks | Advanced tool use | [Introducing GPT-5.4 mini and nano](https://openai.com/index/introducing-gpt-5-4-mini-and-nano/) |
| AutomationBench | 51.8 | 600 public automation tasks | Long-horizon automation | [Kimi K3: Open Frontier Intelligence](https://www.kimi.com/blog/kimi-k3) |
| Agents' Last Exam | 38.5 | Agent tasks | Advanced agentic work | [DeepSeek V4 Flash 0731 update](https://api-docs.deepseek.com/zh-cn/updates/) |
| SpreadsheetBench 2 | 34.9 | Spreadsheet analysis and editing tasks | Professional spreadsheet work | [Kimi K3: Open Frontier Intelligence](https://www.kimi.com/blog/kimi-k3) |
| Claw-Eval | 78.3 | 300 tasks, 2,159 rubrics | Real-world general, multi-turn, and native multimodal agent execution | [Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents](https://arxiv.org/abs/2604.06132) |
| GDPval rubrics | 84.8 | Economically valuable work tasks | Professional agentic workflows | [MiniMax M3 model card](https://huggingface.co/MiniMaxAI/MiniMax-M3) |

### Multimodal & Grounded

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| MathVision w/ Python (MathVision with Python) | 96.5 | Visual mathematics problems with Python | Advanced multimodal mathematics | [Kimi K3: Open Frontier Intelligence](https://www.kimi.com/blog/kimi-k3) |
| Video-MME | 85.2 | Video understanding | Broad multimodal video reasoning | [Video-MME benchmark](https://mme-benchmark.github.io/) |
| Vision2Web | 78.6 | Screenshot-to-web tasks | Multimodal web generation | [GLM-5V-Turbo](https://docs.z.ai/guides/vlm/glm-5v-turbo) |
| CharXiv (CharXiv Reasoning) | 90.2 | 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 |
| --- | --- | --- | --- | --- |
| ResearchRubrics (ResearchRubrics: A Benchmark of Prompts and Rubrics for Evaluating Deep Research Agents) | 81.0 | Deep-research prompts with 2,500+ expert-written rubrics | Open-ended deep research and long-form synthesis | [ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents](https://arxiv.org/abs/2511.07685) |
| FinSearchComp (T3) (FinSearchComp Task 3: Complex Historical Investigation) | 63.4 | Complex historical financial investigation questions (T3 subset of 635 total) | Multi-step financial search and reasoning | [FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning](https://arxiv.org/abs/2509.13160) |
| 3DCodeBench (Text to 3D) (3DCodeBench: Benchmarking Agentic Procedural 3D Modeling via Code (text-to-3D)) | 55.4 | Text prompts to procedural 3D modeling code | Code-level geometric reasoning and 3D software APIs | [3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code](https://arxiv.org/abs/2606.01057) |

## 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.
