Decision support

Ling 3.0 Flash Fin vs GLM 5.3 Flash

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

Models Hardware

Ling 3.0 Flash Fin

InclusionAI

Sources:models.devOpenRouter

GLM 5.3 Flash

Z.ai

Sources:models.devOpenRouter

Benchmark results

DeepSWE 1.1
Best pass@1 · Higher is better
- Ling 3.0 Flash Fin
  Not reported
- GLM 5.3 Flash
  63.4%
  #13 of 28
Runs and sources
Ling 3.0 Flash Fin
Not reported
GLM 5.3 Flash
max63.4%mini-swe-agent · pass@4 85.0% · $0.48 / attempt
Source:DeepSWE leaderboard, 2026-09-22 Official source JSON
Arena Text
Arena rating · Higher is better
- Ling 3.0 Flash Fin
  Not reported
- GLM 5.3 Flash
  1474
  Arena #40CI 1470 to 1479
Runs and sources
Ling 3.0 Flash Fin
Not reported
GLM 5.3 Flash
default147495% CI 1470 to 1479 · 50,189 votes
Source:Arena Text leaderboard, 2026-11-09
Arena WebDev
Arena rating · Higher is better
- Ling 3.0 Flash Fin
  Not reported
- GLM 5.3 Flash
  1609
  Arena #35CI 1603 to 1615
Runs and sources
Ling 3.0 Flash Fin
Not reported
GLM 5.3 Flash
default160995% CI 1603 to 1615 · 23,554 votes
Source:Arena WebDev leaderboard, 2026-11-10
Arena Vision
Arena rating · Higher is better
- Ling 3.0 Flash Fin
  Not reported
- GLM 5.3 Flash
  1272
  Arena #36CI 1266 to 1277
Runs and sources
Ling 3.0 Flash Fin
Not reported
GLM 5.3 Flash
default127295% CI 1266 to 1277 · 31,530 votes
Source:Arena Vision leaderboard, 2026-11-09
Agent Arena
IPS score · Higher is better
- Ling 3.0 Flash Fin
  Not reported
- GLM 5.3 Flash
  -0.029
  Arena #39CI -0.037 to -0.022
Runs and sources
Ling 3.0 Flash Fin
Not reported
GLM 5.3 Flash
default-0.02995% CI -0.037 to -0.022 · 13,770,186 observations
Source:Agent Arena leaderboard, 2026-11-11
ARC-AGI-2
Best published score · Higher is better
- Ling 3.0 Flash Fin
  Not reported
- GLM 5.3 Flash
  65.8%
  #28 of 85
Runs and sources
Ling 3.0 Flash Fin
Not reported
GLM 5.3 Flash
low27.9%
high50.1%
max65.8%
Source:External evaluation via Epoch AIOriginal-source terms apply
FrontierMath-Tier-4-v2-Private
Best published score · Higher is better
- Ling 3.0 Flash Fin
  Not reported
- GLM 5.3 Flash
  17.1%
  #51 of 72
Runs and sources
Ling 3.0 Flash Fin
Not reported
GLM 5.3 Flash
max17.1%
Source:Epoch AI evaluation
FrontierMath-Tiers-1-3-v2-Private
Best published score · Higher is better
- Ling 3.0 Flash Fin
  Not reported
- GLM 5.3 Flash
  55.8%
  #48 of 87
Runs and sources
Ling 3.0 Flash Fin
Not reported
GLM 5.3 Flash
max55.8%
Source:Epoch AI evaluation
GPQA diamond
Best published score · Higher is better
- Ling 3.0 Flash Fin
  Not reported
- GLM 5.3 Flash
  90.2%
  #43 of 161
Runs and sources
Ling 3.0 Flash Fin
Not reported
GLM 5.3 Flash
max90.2%
Source:Epoch AI evaluation
OTIS Mock AIME 2024-2025
Best published score · Higher is better
- Ling 3.0 Flash Fin
  Not reported
- GLM 5.3 Flash
  93.9%
  #46 of 158
Runs and sources
Ling 3.0 Flash Fin
Not reported
GLM 5.3 Flash
max93.9%
Source:Epoch AI evaluation

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.

DeepSWE 1.1 results: official leaderboard, data generated 2026-09-22. Only exact model versions in the official dataset are matched.

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

August 27, 2026

August 26, 2026

Context window

262K

Native context

—

Max output tokens

32,768

131,072

Knowledge cutoff

—

Open weights

Parameter count

127B

321B

API pricing · USD per 1M tokens

Input

$0.042

$0.0399

Output

$0.1232

$0.0784

Cached input

$0.0084

$0.03

Cache write

—

Capabilities and modalities

Input modalities

text

text, image, video

Output modalities

text

Tool calling

Supported

Reasoning option

Supported

Supported options

frequency_penalty, include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, repetition_penalty, seed, stop, temperature, tool_choice, tools, top_k, top_logprobs, top_p

frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, parallel_tool_calls, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

Capabilities

—

completion, thinking, tools, vision

Architecture and availability

Architecture

—

glm5_next

Model families

—

glm5_next

Tokenizer

Other

Instruction format

—

License

MIT

—

Providers

Provider endpoints

Ollama variants

Metadata source

ai-research

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

Benchmark results

DeepSWE 1.1

Arena Text

Arena WebDev

Arena Vision

Agent Arena

ARC-AGI-2

FrontierMath-Tier-4-v2-Private

FrontierMath-Tiers-1-3-v2-Private

GPQA diamond

OTIS Mock AIME 2024-2025

Model specifications

API pricing · USD per 1M tokens

Capabilities and modalities

Architecture and availability