Noometry

Model comparison

GLM-4.7 vs Qwen3 14B

GLM-4.7 is the stronger model overall, scoring 42.0 to 35.5 on the Noometry Index. Qwen3 14B costs 1.6× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.

Last verified . 7 shared benchmarks.

GLM-4.7 Z.ai (Zhipu)

42.0

Rank #124 Confirmed

Qwen3 14B Alibaba (Qwen)

35.5

Rank #225 Confirmed

Summary

  • They share 7 benchmarks with published results for both. GLM-4.7 scores higher in 4 categories and Qwen3 14B in 2 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GLM-4.7 leads 47.0 to 39.3.
  • The biggest single-benchmark swing is GPQA Diamond: 83.3% for GLM-4.7 and 63.8% for Qwen3 14B.
  • Qwen3 14B is cheaper at $0.35 / $1.40 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
  • GLM-4.7 accepts more context: 205K tokens versus 131K.

Side by side

GLM-4.7Qwen3 14B
ProviderZ.ai (Zhipu)Alibaba (Qwen)
Noometry Index42.035.5
Released2025-12-222025-04
WeightsOpenOpen
Context window205K131K
Max output131K8K
Input $ / M tokens$0.60$0.35
Output $ / M tokens$2.20$1.40
Results tracked3612

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

Category by category

Coding GLM-4.7 leads

GLM-4.7: 44.0 (#79), Qwen3 14B: 37.3 (#195)

BenchmarkGLM-4.7Qwen3 14B
SciCode45.1%31.6%
LMArena WebDev1435—
LMArena Coding1454—
ALE-Bench399.48—

Agentic & Tool Use Qwen3 14B leads

GLM-4.7: 26.5 (#103), Qwen3 14B: 29.6 (#83)

BenchmarkGLM-4.7Qwen3 14B
Terminal-Bench33.4%—
Berkeley Function Calling Leaderboard—41%
Vending-Bench 22,377—

Reasoning GLM-4.7 leads

GLM-4.7: 24.3 (#164), Qwen3 14B: 18.5 (#280)

BenchmarkGLM-4.7Qwen3 14B
CritPt1.7%0%
Chess Puzzles6%4%
Epoch Capabilities Index143.51138.23
SimpleBench47.7%—
Kagi LLM Benchmark—49.1%
LMArena Hard Prompts1443—
DTBench—64%
LMCA—18.2%

Math Too close to call

GLM-4.7: 38.6 (#135), Qwen3 14B: 38.6 (#133)

BenchmarkGLM-4.7Qwen3 14B
OTIS Mock AIME 2024-202583.3%66.4%
ProofBench6%—
LMArena Math1423—
FrontierMath (Feb 2025 set)2.4%—
FrontierMath Tier 4 (v1)0%—

Knowledge GLM-4.7 leads

GLM-4.7: 47.0 (#80), Qwen3 14B: 39.3 (#134)

BenchmarkGLM-4.7Qwen3 14B
GPQA Diamond83.3%63.8%
Vectara Hallucination Rate11.7%5.4%
SimpleQA Verified32.2%—
LMArena Expert1424—

Multilingual Not comparable

GLM-4.7: 52.8 (#79), Qwen3 14B: —

BenchmarkGLM-4.7Qwen3 14B
LMArena Non-English1417—
LMArena Chinese1495—
LMArena French1432—
LMArena German1424—
LMArena Japanese1439—
LMArena Korean1399—
LMArena Russian1423—
LMArena Spanish1434—

Instruction Following Not comparable

GLM-4.7: 74.4 (#95), Qwen3 14B: —

BenchmarkGLM-4.7Qwen3 14B
LMArena Instruction Following1411—

Long Context GLM-4.7 leads

GLM-4.7: 42.8 (#116), Qwen3 14B: 38.1 (#204)

BenchmarkGLM-4.7Qwen3 14B
Fiction.LiveBench—62.5%
CL-bench15.9%—
CL-bench Life10.9%—
LMArena Longer Query1432—

Writing & Preference Not comparable

GLM-4.7: 60.9 (#93), Qwen3 14B: —

BenchmarkGLM-4.7Qwen3 14B
LMArena Text1435—
LMArena Creative Writing1401—
EQ-Bench Creative Writing1413—
LMArena Multi-Turn1446—

Frequently asked questions

Is GLM-4.7 better than Qwen3 14B?

GLM-4.7 is the stronger model overall, scoring 42.0 to 35.5 on the Noometry Index. Qwen3 14B costs 1.6× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.

Which is cheaper, GLM-4.7 or Qwen3 14B?

Qwen3 14B is cheaper. It lists at $0.35 per million input tokens and $1.40 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.

Is GLM-4.7 or Qwen3 14B better for coding?

GLM-4.7 scores higher on coding benchmarks: 44.0 versus 37.3 in the Noometry coding category.

Which has the bigger context window?

GLM-4.7 does, with 205K tokens against 131K.

How many benchmarks do GLM-4.7 and Qwen3 14B share?

7 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Qwen3 14B has 12.

Related comparisons

Go deeper