Model comparison

DeepSeek V4.1 Flash vs GLM-5.3-Flash

DeepSeek V4.1 Flash and GLM-5.3-Flash score almost the same on the Noometry Index (52.8 vs 51.8), so choose on price, context window or the category you care about most.

Last verified October 10, 2026. 32 shared benchmarks.

DeepSeek V4.1 Flash

DeepSeek

52.8

Rank #38 Confirmed

GLM-5.3-Flash Z.ai (Zhipu)

51.8

Rank #41 Confirmed

Summary

They share 32 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 3 categories and GLM-5.3-Flash in 7 categories; 5 gaps are clear of the uncertainty.
The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 53.3.
The biggest single-benchmark swing is Mystery Game Puzzles: 43% for DeepSeek V4.1 Flash and 8% for GLM-5.3-Flash.
GLM-5.3-Flash is cheaper at $0.15 / $0.50 per million input/output tokens, against $0.15 / $0.60 for DeepSeek V4.1 Flash.

Side by side

DeepSeek V4.1 Flash and GLM-5.3-Flash specifications
	DeepSeek V4.1 Flash	GLM-5.3-Flash
Provider	DeepSeek	Z.ai (Zhipu)
Noometry Index	52.8	51.8
Released	2026-09-09	2026-08-20
Weights	Open	Open
Context window	1M	1M
Max output	393K	131K
Input $ / M tokens	$0.15	$0.15
Output $ / M tokens	$0.60	$0.50
Results tracked	37	40

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Too close to call

DeepSeek V4.1 Flash: 52.9 (#32), GLM-5.3-Flash: 53.1 (#31)

Coding benchmarks
Benchmark	DeepSeek V4.1 Flash	GLM-5.3-Flash
LMArena WebDev	1619	1609
SciCode	51.9%	51.6%
LMArena Coding	1506	1508
ALE-Bench	1,092	303.55
DeepSWE	—	63.4%
FrontierCode	—	31.8%
CursorBench	—	36.8%
FrontierSWE	—	18.1%

Agentic & Tool Use GLM-5.3-Flash leads

DeepSeek V4.1 Flash: 31.2 (#69), GLM-5.3-Flash: 34.2 (#47)

Agentic & Tool Use benchmarks
Benchmark	DeepSeek V4.1 Flash	GLM-5.3-Flash
APEX-Agents	39.5%	52.8%
GDP.pdf	19.8%	14%

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 50.2 (#36), GLM-5.3-Flash: 48.0 (#42)

Reasoning benchmarks
Benchmark	DeepSeek V4.1 Flash	GLM-5.3-Flash
CritPt	14.3%	15.4%
LMArena Hard Prompts	1483	1491
Mystery Game Puzzles	43%	8%
Surface Evolver Bench	46.3%	52.5%
Epoch Capabilities Index	154.9	151.88
ARC-AGI-2	—	65.8%
NYT Connections (extended)	89.6%	—
ARC-AGI-1	—	91%
Chess Puzzles	—	14%
DTBench	89.9%	—
LMCA	47%	—
Bench to the Future 3	—	0.15

Math DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 66.7 (#25), GLM-5.3-Flash: 53.3 (#47)

Math benchmarks
Benchmark	DeepSeek V4.1 Flash	GLM-5.3-Flash
FrontierMath (Tiers 1-3)	67.4%	55.8%
FrontierMath Tier 4	26.8%	17.1%
OTIS Mock AIME 2024-2025	98.3%	93.9%
ProofBench	54%	21%
LMArena Math	1477	1500

Knowledge Too close to call

DeepSeek V4.1 Flash: 57.9 (#38), GLM-5.3-Flash: 58.4 (#36)

Knowledge benchmarks
Benchmark	DeepSeek V4.1 Flash	GLM-5.3-Flash
GPQA Diamond	89.8%	90.2%
LMArena Expert	1506	1513

Multimodal GLM-5.3-Flash leads

DeepSeek V4.1 Flash: 39.1 (#61), GLM-5.3-Flash: 42.8 (#27)

Multimodal benchmarks
Benchmark	DeepSeek V4.1 Flash	GLM-5.3-Flash
LMArena Vision	1277	1296
Furniture Assembly	34.2%	—

Multilingual GLM-5.3-Flash leads

DeepSeek V4.1 Flash: 55.0 (#35), GLM-5.3-Flash: 56.0 (#25)

Multilingual benchmarks
Benchmark	DeepSeek V4.1 Flash	GLM-5.3-Flash
LMArena Non-English	1448	1462
LMArena Chinese	1497	1527
LMArena French	1452	1496
LMArena German	1484	1470
LMArena Japanese	1412	1429
LMArena Korean	1452	1446
LMArena Russian	1471	1469
LMArena Spanish	1459	1471

Instruction Following Too close to call

DeepSeek V4.1 Flash: 77.3 (#26), GLM-5.3-Flash: 77.5 (#20)

Instruction Following benchmarks
Benchmark	DeepSeek V4.1 Flash	GLM-5.3-Flash
LMArena Instruction Following	1474	1478

Long Context Too close to call

DeepSeek V4.1 Flash: 45.2 (#47), GLM-5.3-Flash: 45.4 (#39)

Long Context benchmarks
Benchmark	DeepSeek V4.1 Flash	GLM-5.3-Flash
LMArena Longer Query	1475	1482

Writing & Preference Too close to call

DeepSeek V4.1 Flash: 65.4 (#48), GLM-5.3-Flash: 65.3 (#50)

Writing & Preference benchmarks
Benchmark	DeepSeek V4.1 Flash	GLM-5.3-Flash
LMArena Text	1462	1471
LMArena Creative Writing	1435	1442
LMArena Multi-Turn	1457	1467
EQ-Bench Creative Writing	1540	—

Frequently asked questions

Is DeepSeek V4.1 Flash better than GLM-5.3-Flash?

DeepSeek V4.1 Flash and GLM-5.3-Flash score almost the same on the Noometry Index (52.8 vs 51.8), so choose on price, context window or the category you care about most.

Which is cheaper, DeepSeek V4.1 Flash or GLM-5.3-Flash?

GLM-5.3-Flash is cheaper. It lists at $0.15 per million input tokens and $0.50 per million output tokens; DeepSeek V4.1 Flash lists at $0.15 and $0.60.

Is DeepSeek V4.1 Flash or GLM-5.3-Flash better for coding?

They score almost the same on coding (52.9 vs 53.1); test both on your own repository before choosing.

Which has the bigger context window?

Both accept 1M tokens.

How many benchmarks do DeepSeek V4.1 Flash and GLM-5.3-Flash share?

32 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and GLM-5.3-Flash has 40.