Noometry

Model comparison

GLM-4.7-Flash vs Qwen3 14B

GLM-4.7-Flash is the stronger model overall, scoring 38.8 to 35.5 on the Noometry Index.

Last verified . 4 shared benchmarks.

GLM-4.7-Flash Z.ai (Zhipu)

38.8

Rank #180 Confirmed

Qwen3 14B Alibaba (Qwen)

35.5

Rank #225 Confirmed

Summary

  • They share 4 benchmarks with published results for both. GLM-4.7-Flash scores higher in 3 categories and Qwen3 14B in 2 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3 14B leads 39.3 to 35.5.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 58.3% for GLM-4.7-Flash and 66.4% for Qwen3 14B.
  • GLM-4.7-Flash is cheaper at $0.06 / $0.40 per million input/output tokens, against $0.35 / $1.40 for Qwen3 14B.
  • GLM-4.7-Flash accepts more context: 200K tokens versus 131K.

Side by side

GLM-4.7-FlashQwen3 14B
ProviderZ.ai (Zhipu)Alibaba (Qwen)
Noometry Index38.835.5
Released2026-01-192025-04
WeightsOpenOpen
Context window200K131K
Max output131K8K
Input $ / M tokens$0.06$0.35
Output $ / M tokens$0.40$1.40
Results tracked2112

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

Category by category

Coding GLM-4.7-Flash leads

GLM-4.7-Flash: 40.6 (#135), Qwen3 14B: 37.3 (#195)

BenchmarkGLM-4.7-FlashQwen3 14B
SciCode—31.6%
LMArena Coding1383—

Agentic & Tool Use Not comparable

GLM-4.7-Flash: —, Qwen3 14B: 29.6 (#83)

BenchmarkGLM-4.7-FlashQwen3 14B
Berkeley Function Calling Leaderboard—41%

Reasoning GLM-4.7-Flash leads

GLM-4.7-Flash: 20.9 (#229), Qwen3 14B: 18.5 (#280)

BenchmarkGLM-4.7-FlashQwen3 14B
Chess Puzzles0%4%
Kagi LLM Benchmark—49.1%
CritPt—0%
LMArena Hard Prompts1356—
DTBench—64%
LMCA—18.2%
Epoch Capabilities Index—138.23

Math Qwen3 14B leads

GLM-4.7-Flash: 36.1 (#173), Qwen3 14B: 38.6 (#133)

BenchmarkGLM-4.7-FlashQwen3 14B
OTIS Mock AIME 2024-202558.3%66.4%
LMArena Math1355—

Knowledge Qwen3 14B leads

GLM-4.7-Flash: 35.5 (#184), Qwen3 14B: 39.3 (#134)

BenchmarkGLM-4.7-FlashQwen3 14B
GPQA Diamond60.5%63.8%
Vectara Hallucination Rate9.3%5.4%
LMArena Expert1357—

Multilingual Not comparable

GLM-4.7-Flash: 46.5 (#158), Qwen3 14B: —

BenchmarkGLM-4.7-FlashQwen3 14B
LMArena Non-English1330—
LMArena Chinese1403—
LMArena French1332—
LMArena German1337—
LMArena Korean1283—
LMArena Russian1332—
LMArena Spanish1350—

Instruction Following Not comparable

GLM-4.7-Flash: 70.1 (#167), Qwen3 14B: —

BenchmarkGLM-4.7-FlashQwen3 14B
LMArena Instruction Following1327—

Long Context GLM-4.7-Flash leads

GLM-4.7-Flash: 40.9 (#148), Qwen3 14B: 38.1 (#204)

BenchmarkGLM-4.7-FlashQwen3 14B
Fiction.LiveBench—62.5%
LMArena Longer Query1345—

Writing & Preference Not comparable

GLM-4.7-Flash: 47.4 (#210), Qwen3 14B: —

BenchmarkGLM-4.7-FlashQwen3 14B
LMArena Text1351—
LMArena Creative Writing1297—
EQ-Bench Creative Writing1125—
LMArena Multi-Turn1342—

Frequently asked questions

Is GLM-4.7-Flash better than Qwen3 14B?

GLM-4.7-Flash is the stronger model overall, scoring 38.8 to 35.5 on the Noometry Index.

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

GLM-4.7-Flash is cheaper. It lists at $0.06 per million input tokens and $0.40 per million output tokens; Qwen3 14B lists at $0.35 and $1.40.

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

GLM-4.7-Flash scores higher on coding benchmarks: 40.6 versus 37.3 in the Noometry coding category.

Which has the bigger context window?

GLM-4.7-Flash does, with 200K tokens against 131K.

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

4 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and Qwen3 14B has 12.

Related comparisons

Go deeper