Model comparison

DeepSeek-V3 vs GLM-4.7-Flash

DeepSeek-V3 and GLM-4.7-Flash score almost the same on the Noometry Index (39.2 vs 38.4), so choose on price, context window or the category you care about most.

Last verified October 10, 2026. 20 shared benchmarks.

DeepSeek-V3

DeepSeek

39.2

Rank #157 Confirmed

GLM-4.7-Flash Z.ai (Zhipu)

38.4

Rank #175 Confirmed

Summary

They share 20 benchmarks with published results for both. DeepSeek-V3 scores higher in 5 categories and GLM-4.7-Flash in 3 categories; 7 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where DeepSeek-V3 leads 57.6 to 47.7.
The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 37.8% for DeepSeek-V3 and 58.3% for GLM-4.7-Flash.
GLM-4.7-Flash is cheaper at $0.06 / $0.40 per million input/output tokens, against $0.24 / $0.90 for DeepSeek-V3.
GLM-4.7-Flash accepts more context: 200K tokens versus 164K.

Side by side

DeepSeek-V3 and GLM-4.7-Flash specifications
	DeepSeek-V3	GLM-4.7-Flash
Provider	DeepSeek	Z.ai (Zhipu)
Noometry Index	39.2	38.4
Released	2024-12-26	2026-01-19
Weights	Open	Open
Context window	164K	200K
Max output	164K	131K
Input $ / M tokens	$0.24	$0.06
Output $ / M tokens	$0.90	$0.40
Results tracked	60	21

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

Category by category

Coding DeepSeek-V3 leads

DeepSeek-V3: 41.9 (#99), GLM-4.7-Flash: 40.0 (#133)

Coding benchmarks
Benchmark	DeepSeek-V3	GLM-4.7-Flash
LMArena Coding	1368	1383
Aider Polyglot	55.1%	—
SciCode	35.8%	—
WeirdML	36.1%	—
BigCodeBench Instruct	50%	—
LiveBench Coding	70.9%	—
BigCodeBench Complete	62.2%	—
HumanEval+	86.6%	—
MBPP+	73%	—

Agentic & Tool Use Not comparable

DeepSeek-V3: —, GLM-4.7-Flash: —

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-V3	GLM-4.7-Flash
METR Time Horizons	49.6%	—

Reasoning Too close to call

DeepSeek-V3: 20.0 (#226), GLM-4.7-Flash: 20.2 (#224)

Reasoning benchmarks
Benchmark	DeepSeek-V3	GLM-4.7-Flash
LMArena Hard Prompts	1365	1356
SimpleBench	27.2%	—
Kagi LLM Benchmark	52.3%	—
CritPt	0%	—
Chess Puzzles	—	0%
LiveBench Reasoning	65.8%	—
DTBench	64.8%	—
LiveBench Data Analysis	60.9%	—
LMCA	15.5%	—
BIG-Bench Hard	87.5%	—
Epoch Capabilities Index	135.95	—
ForecastBench	59.1	—
HellaSwag	88.9%	—
LiveBench	66.9%	—
PIQA	84.7%	—
WinoGrande	85.2%	—

Math GLM-4.7-Flash leads

DeepSeek-V3: 30.4 (#208), GLM-4.7-Flash: 34.4 (#159)

Math benchmarks
Benchmark	DeepSeek-V3	GLM-4.7-Flash
OTIS Mock AIME 2024-2025	37.8%	58.3%
LMArena Math	1373	1354
Omni-MATH	40.3%	—
LiveBench Math	73.5%	—
MATH Level 5	75.5%	—
FrontierMath (Feb 2025 set)	1.7%	—

Knowledge DeepSeek-V3 leads

DeepSeek-V3: 37.5 (#147), GLM-4.7-Flash: 35.4 (#177)

Knowledge benchmarks
Benchmark	DeepSeek-V3	GLM-4.7-Flash
GPQA Diamond	67.6%	60.5%
Vectara Hallucination Rate	6.1%	9.3%
LMArena Expert	1352	1357
MMLU-Pro	72.3%	—
Confabulations	26.1%	—
GPQA (HELM)	53.8%	—
ARC (AI2) Challenge	95.3%	—
MMLU	87.2%	—
TriviaQA	82.9%	—

Multilingual DeepSeek-V3 leads

DeepSeek-V3: 48.8 (#138), GLM-4.7-Flash: 46.8 (#152)

Multilingual benchmarks
Benchmark	DeepSeek-V3	GLM-4.7-Flash
LMArena Non-English	1358	1331
LMArena Chinese	1390	1403
LMArena French	1386	1332
LMArena German	1374	1336
LMArena Korean	1321	1284
LMArena Russian	1372	1333
LMArena Spanish	1358	1351
LMArena Japanese	1333	—

Instruction Following DeepSeek-V3 leads

DeepSeek-V3: 73.0 (#125), GLM-4.7-Flash: 70.3 (#162)

Instruction Following benchmarks
Benchmark	DeepSeek-V3	GLM-4.7-Flash
LMArena Instruction Following	1345	1327
LiveBench Instruction Following	81.5%	—
IFEval	83.2%	—

Long Context GLM-4.7-Flash leads

DeepSeek-V3: 34.0 (#248), GLM-4.7-Flash: 40.9 (#143)

Long Context benchmarks
Benchmark	DeepSeek-V3	GLM-4.7-Flash
LMArena Longer Query	1353	1345
Fiction.LiveBench	50%	—

Writing & Preference DeepSeek-V3 leads

DeepSeek-V3: 57.6 (#124), GLM-4.7-Flash: 47.7 (#206)

Writing & Preference benchmarks
Benchmark	DeepSeek-V3	GLM-4.7-Flash
LMArena Text	1375	1351
LMArena Creative Writing	1364	1297
EQ-Bench Creative Writing	1472	1125
LMArena Multi-Turn	1389	1342
Short-Story Creative Writing	77%	—
WildBench	83%	—
LiveBench Language	49.1%	—

Frequently asked questions

Is DeepSeek-V3 better than GLM-4.7-Flash?

DeepSeek-V3 and GLM-4.7-Flash score almost the same on the Noometry Index (39.2 vs 38.4), so choose on price, context window or the category you care about most.

Which is cheaper, DeepSeek-V3 or GLM-4.7-Flash?

GLM-4.7-Flash is cheaper. It lists at $0.06 per million input tokens and $0.40 per million output tokens; DeepSeek-V3 lists at $0.24 and $0.90.

Is DeepSeek-V3 or GLM-4.7-Flash better for coding?

DeepSeek-V3 scores higher on coding benchmarks: 41.9 versus 40.0 in the Noometry coding category.

Which has the bigger context window?

GLM-4.7-Flash does, with 200K tokens against 164K.

How many benchmarks do DeepSeek-V3 and GLM-4.7-Flash share?

20 benchmarks have published results for both models. DeepSeek-V3 has 60 scored results on Noometry and GLM-4.7-Flash has 21.