Model comparison

DeepSeek V4.1 Flash vs GLM-5.2

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 51.1 on the Noometry Index.

Last verified October 10, 2026. 34 shared benchmarks.

DeepSeek V4.1 Flash

DeepSeek

52.8

Rank #38 Confirmed

GLM-5.2 Z.ai (Zhipu)

51.1

Rank #44 Confirmed

Summary

They share 34 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 5 categories and GLM-5.2 in 4 categories; 5 gaps are clear of the uncertainty.
The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 55.7.
The biggest single-benchmark swing is Mystery Game Puzzles: 43% for DeepSeek V4.1 Flash and 19% for GLM-5.2.
DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.

Side by side

DeepSeek V4.1 Flash and GLM-5.2 specifications
	DeepSeek V4.1 Flash	GLM-5.2
Provider	DeepSeek	Z.ai (Zhipu)
Noometry Index	52.8	51.1
Released	2026-09-09	2026-06-13
Weights	Open	Open
Context window	1M	1M
Max output	393K	131K
Input $ / M tokens	$0.15	$1.40
Output $ / M tokens	$0.60	$4.40
Results tracked	37	51

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

Category by category

Coding DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 52.9 (#32), GLM-5.2: 51.3 (#41)

Coding benchmarks
Benchmark	DeepSeek V4.1 Flash	GLM-5.2
LMArena WebDev	1619	1603
SciCode	51.9%	50.5%
LMArena Coding	1506	1485
ALE-Bench	1,092	1,047
SWE-bench Verified	—	78.7%
DeepSWE	—	43.8%
FrontierCode	—	24.5%
WeirdML	—	70.1%

Agentic & Tool Use GLM-5.2 leads

DeepSeek V4.1 Flash: 31.2 (#69), GLM-5.2: 32.4 (#63)

Agentic & Tool Use benchmarks
Benchmark	DeepSeek V4.1 Flash	GLM-5.2
APEX-Agents	39.5%	45.2%
τ²-bench Banking	—	37.1%
PostTrainBench	—	31.7%
GBAEval	—	0%
GDP.pdf	19.8%	—
Vending-Bench 2	—	8,314

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 50.2 (#36), GLM-5.2: 42.3 (#52)

Reasoning benchmarks
Benchmark	DeepSeek V4.1 Flash	GLM-5.2
NYT Connections (extended)	89.6%	74.3%
CritPt	14.3%	20.9%
LMArena Hard Prompts	1483	1480
Mystery Game Puzzles	43%	19%
DTBench	89.9%	93.6%
LMCA	47%	45.8%
Surface Evolver Bench	46.3%	55.6%
Epoch Capabilities Index	154.9	151.78
ARC-AGI-2	—	22.8%
SimpleBench	—	58.8%
Kagi LLM Benchmark	—	62.6%
ARC-AGI-1	—	77%
Chess Puzzles	—	21%
EBR-Bench	—	9.5%

Math DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 66.7 (#25), GLM-5.2: 55.7 (#43)

Math benchmarks
Benchmark	DeepSeek V4.1 Flash	GLM-5.2
FrontierMath (Tiers 1-3)	67.4%	59.2%
FrontierMath Tier 4	26.8%	29.3%
OTIS Mock AIME 2024-2025	98.3%	86.4%
ProofBench	54%	35%
LMArena Math	1477	1482
MathArena Final-Answer Competitions	—	67.6%

Knowledge Too close to call

DeepSeek V4.1 Flash: 57.9 (#38), GLM-5.2: 57.1 (#40)

Knowledge benchmarks
Benchmark	DeepSeek V4.1 Flash	GLM-5.2
GPQA Diamond	89.8%	91.9%
LMArena Expert	1506	1486
SimpleQA Verified	—	34.2%

Multimodal Not comparable

DeepSeek V4.1 Flash: 39.1 (#61), GLM-5.2: —

Multimodal benchmarks
Benchmark	DeepSeek V4.1 Flash	GLM-5.2
LMArena Vision	1277	—
Furniture Assembly	34.2%	—

Multilingual Too close to call

DeepSeek V4.1 Flash: 55.0 (#35), GLM-5.2: 55.8 (#26)

Multilingual benchmarks
Benchmark	DeepSeek V4.1 Flash	GLM-5.2
LMArena Non-English	1448	1459
LMArena Chinese	1497	1519
LMArena French	1452	1479
LMArena German	1484	1468
LMArena Japanese	1412	1451
LMArena Korean	1452	1445
LMArena Russian	1471	1466
LMArena Spanish	1459	1477

Instruction Following Too close to call

DeepSeek V4.1 Flash: 77.3 (#26), GLM-5.2: 76.9 (#34)

Instruction Following benchmarks
Benchmark	DeepSeek V4.1 Flash	GLM-5.2
LMArena Instruction Following	1474	1465

Long Context Too close to call

DeepSeek V4.1 Flash: 45.2 (#47), GLM-5.2: 45.3 (#43)

Long Context benchmarks
Benchmark	DeepSeek V4.1 Flash	GLM-5.2
LMArena Longer Query	1475	1479

Writing & Preference GLM-5.2 leads

DeepSeek V4.1 Flash: 65.4 (#48), GLM-5.2: 70.4 (#21)

Writing & Preference benchmarks
Benchmark	DeepSeek V4.1 Flash	GLM-5.2
LMArena Text	1462	1470
LMArena Creative Writing	1435	1462
EQ-Bench Creative Writing	1540	1757
LMArena Multi-Turn	1457	1469
EQ-Bench 4	—	1222

Frequently asked questions

Is DeepSeek V4.1 Flash better than GLM-5.2?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 51.1 on the Noometry Index.

Which is cheaper, DeepSeek V4.1 Flash or GLM-5.2?

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GLM-5.2 lists at $1.40 and $4.40.

Is DeepSeek V4.1 Flash or GLM-5.2 better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 51.3 in the Noometry coding category.

Which has the bigger context window?

Both accept 1M tokens.

How many benchmarks do DeepSeek V4.1 Flash and GLM-5.2 share?

34 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and GLM-5.2 has 51.