Decision support

LongCat-2.5 vs Inkling 2 Small

Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.

Models Hardware

LongCat-2.5

Meituan

Sources:models.dev

Inkling 2 Small

Thinking Machines Lab

Sources:models.devOpenRouter

Benchmark results

Arena Text
Arena rating · Higher is better
- LongCat-2.5
  Not reported
- Inkling 2 Small
  1412
  Arena #151CI 1400 to 1424
Runs and sources
LongCat-2.5
Not reported
Inkling 2 Small
default141295% CI 1400 to 1424 · 2,668 votes
Source:Arena Text leaderboard, 2026-11-09
Arena WebDev
Arena rating · Higher is better
- LongCat-2.5
  Not reported
- Inkling 2 Small
  1646
  Arena #22CI 1627 to 1666
Runs and sources
LongCat-2.5
Not reported
Inkling 2 Small
default164695% CI 1627 to 1666 · 983 votes
Source:Arena WebDev leaderboard, 2026-11-10
Agent Arena
IPS score · Higher is better
- LongCat-2.5
  Not reported
- Inkling 2 Small
  +0.025
  Arena #18CI +0.010 to +0.040
Runs and sources
LongCat-2.5
Not reported
Inkling 2 Small
default+0.02595% CI +0.010 to +0.040 · 1,511,880 observations
Source:Agent Arena leaderboard, 2026-11-11
ARC-AGI-2
Best published score · Higher is better
- LongCat-2.5
  Not reported
- Inkling 2 Small
  81.7%
  #19 of 85
Runs and sources
LongCat-2.5
Not reported
Inkling 2 Small
xhigh81.7%
Source:External evaluation via Epoch AIOriginal-source terms apply

Each model's best published result is shown; "Not reported" means no matched evaluation, not a score of zero. Arena and DeepSWE ranks are the leaderboards' own; other ranks are among catalogue models with a score. Results from different harnesses or settings are not directly comparable.

Original-source terms apply to evaluations credited to their original publishers.

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.

Model specifications

Release date

November 2, 2026

November 5, 2026

Context window

Native context

—

Max output tokens

262,144

131,072

Knowledge cutoff

—

Open weights

Closed

Parameter count

—

API pricing · USD per 1M tokens

Input

—

$0.00

Output

—

$0.00

Cached input

—

Cache write

—

Capabilities and modalities

Input modalities

text, image

Output modalities

text

Tool calling

Supported

Reasoning option

Supported

Supported options

tools, reasoning

include_reasoning, max_tokens, reasoning, reasoning_effort, seed, stop, temperature, tools, top_p

Capabilities

—

Architecture and availability

Architecture

—

Model families

—

Tokenizer

—

Other

Instruction format

—

License

—

Proprietary

Providers

Provider endpoints

Ollama variants

Metadata source

ai-research

models.dev

A dash means the field is not reported. Provider-specific performance and pricing may differ.

Benchmark results

Arena Text

Arena WebDev

Agent Arena

ARC-AGI-2

Model specifications

API pricing · USD per 1M tokens

Capabilities and modalities

Architecture and availability