Noometry

Model comparison

GLM-4.6 vs Qwen2.5 7B Instruct

GLM-4.6 is the stronger model overall, scoring 41.4 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 3.3× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.

Last verified . 0 shared benchmarks.

GLM-4.6 Z.ai (Zhipu)

41.4

Rank #135 Confirmed

Qwen2.5 7B Instruct Alibaba (Qwen)

29.0

Rank #320 Confirmed

Summary

  • The widest gap is in math, where GLM-4.6 leads 39.1 to 12.6.
  • Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
  • GLM-4.6 accepts more context: 205K tokens versus 131K.

Side by side

GLM-4.6Qwen2.5 7B Instruct
ProviderZ.ai (Zhipu)Alibaba (Qwen)
Noometry Index41.429.0
Released2025-09-302024-09
WeightsOpenOpen
Context window205K131K
Max output131K8K
Input $ / M tokens$0.60$0.17
Output $ / M tokens$2.20$0.70
Results tracked2915

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

Category by category

Coding GLM-4.6 leads

GLM-4.6: 40.1 (#148), Qwen2.5 7B Instruct: 36.5 (#208)

BenchmarkGLM-4.6Qwen2.5 7B Instruct
SWE-bench Verified (bash only)55.4%—
LMArena WebDev1340—
SciCode38.4%—
BigCodeBench Instruct—37.6%
LMArena Coding1449—
BigCodeBench Complete—46.1%
ALE-Bench340.82—

Agentic & Tool Use GLM-4.6 leads

GLM-4.6: 32.3 (#66), Qwen2.5 7B Instruct: 23.8 (#124)

BenchmarkGLM-4.6Qwen2.5 7B Instruct
Terminal-Bench24.5%—
Berkeley Function Calling Leaderboard72.4%—
BALROG—7.8%

Reasoning GLM-4.6 leads

GLM-4.6: 23.7 (#172), Qwen2.5 7B Instruct: 14.8 (#322)

BenchmarkGLM-4.6Qwen2.5 7B Instruct
Kagi LLM Benchmark47.4%—
CritPt1.1%—
Chess Puzzles—0%
LMArena Hard Prompts1440—
DTBench—47.7%
LMCA—6.4%
Epoch Capabilities Index—118.51

Math GLM-4.6 leads

GLM-4.6: 39.1 (#111), Qwen2.5 7B Instruct: 12.6 (#306)

BenchmarkGLM-4.6Qwen2.5 7B Instruct
OTIS Mock AIME 2024-2025—2.5%
Omni-MATH—29.4%
LMArena Math1432—
FrontierMath (Feb 2025 set)3.8%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge GLM-4.6 leads

GLM-4.6: 40.2 (#124), Qwen2.5 7B Instruct: 17.0 (#286)

BenchmarkGLM-4.6Qwen2.5 7B Instruct
GPQA Diamond—35.5%
MMLU-Pro—53.9%
Vectara Hallucination Rate9.5%—
GPQA (HELM)—34.1%
LMArena Expert1431—
MMLU—72.9%

Multilingual Not comparable

GLM-4.6: 53.5 (#66), Qwen2.5 7B Instruct: —

BenchmarkGLM-4.6Qwen2.5 7B Instruct
LMArena Non-English1426—
LMArena Chinese1499—
LMArena French1459—
LMArena German1447—
LMArena Japanese1393—
LMArena Korean1400—
LMArena Russian1419—
LMArena Spanish1436—

Instruction Following GLM-4.6 leads

GLM-4.6: 74.3 (#98), Qwen2.5 7B Instruct: 63.2 (#231)

BenchmarkGLM-4.6Qwen2.5 7B Instruct
IFEval—74.1%
LMArena Instruction Following1410—

Long Context Not comparable

GLM-4.6: 43.4 (#94), Qwen2.5 7B Instruct: —

BenchmarkGLM-4.6Qwen2.5 7B Instruct
LMArena Longer Query1422—

Writing & Preference GLM-4.6 leads

GLM-4.6: 61.1 (#90), Qwen2.5 7B Instruct: 48.8 (#195)

BenchmarkGLM-4.6Qwen2.5 7B Instruct
LMArena Text1440—
LMArena Creative Writing1411—
EQ-Bench Creative Writing1411—
WildBench—73.1%
LMArena Multi-Turn1427—

Frequently asked questions

Is GLM-4.6 better than Qwen2.5 7B Instruct?

GLM-4.6 is the stronger model overall, scoring 41.4 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 3.3× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.

Which is cheaper, GLM-4.6 or Qwen2.5 7B Instruct?

Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.

Is GLM-4.6 or Qwen2.5 7B Instruct better for coding?

GLM-4.6 scores higher on coding benchmarks: 40.1 versus 36.5 in the Noometry coding category.

Which has the bigger context window?

GLM-4.6 does, with 205K tokens against 131K.

How many benchmarks do GLM-4.6 and Qwen2.5 7B Instruct share?

0 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Qwen2.5 7B Instruct has 15.

Related comparisons

Go deeper