Noometry

Model comparison

GLM-5.3-Flash vs Reka Flash 3

GLM-5.3-Flash has enough public results to be ranked (#45); Reka Flash 3 does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

GLM-5.3-Flash Z.ai (Zhipu)

49.6

Rank #45 Confirmed

Reka Flash 3 Reka

36.4

Unranked Sparse

Summary

  • The widest gap is in writing & preference, where GLM-5.3-Flash leads 65.4 to 43.8.
  • Reka Flash 3 is cheaper at $0.10 / $0.20 per million input/output tokens, against $0.15 / $0.50 for GLM-5.3-Flash.
  • GLM-5.3-Flash accepts more context: 1M tokens versus 66K.

Side by side

GLM-5.3-FlashReka Flash 3
ProviderZ.ai (Zhipu)Reka
Noometry Index49.636.4
Released2026-08-202025-03-10
WeightsOpenOpen
Context window1M66K
Max output131K59K
Input $ / M tokens$0.15$0.10
Output $ / M tokens$0.50$0.20
Results tracked362

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

Category by category

Coding Not comparable

GLM-5.3-Flash: 53.7 (#26), Reka Flash 3: —

BenchmarkGLM-5.3-FlashReka Flash 3
DeepSWE63.4%—
FrontierCode31.8%—
LMArena WebDev1614—
SciCode51.6%—
LMArena Coding1506—
ALE-Bench303.55—

Agentic & Tool Use GLM-5.3-Flash leads

GLM-5.3-Flash: 34.3 (#41), Reka Flash 3: 30.1

BenchmarkGLM-5.3-FlashReka Flash 3
APEX-Agents52.8%—
BALROG—29.2%
GDP.pdf14%—

Reasoning Not comparable

GLM-5.3-Flash: 31.7 (#69), Reka Flash 3: —

BenchmarkGLM-5.3-FlashReka Flash 3
CritPt15.4%—
Chess Puzzles14%—
LMArena Hard Prompts1490—
Mystery Game Puzzles8%—
Surface Evolver Bench52.5%—
Bench to the Future 30.15—
Epoch Capabilities Index151.9—

Math Not comparable

GLM-5.3-Flash: 53.1 (#38), Reka Flash 3: —

BenchmarkGLM-5.3-FlashReka Flash 3
FrontierMath (Tiers 1-3)55.8%—
FrontierMath Tier 417.1%—
OTIS Mock AIME 2024-202593.9%—
ProofBench21%—
LMArena Math1499—

Knowledge Not comparable

GLM-5.3-Flash: 58.4 (#33), Reka Flash 3: —

BenchmarkGLM-5.3-FlashReka Flash 3
GPQA Diamond90.2%—
LMArena Expert1512—

Multimodal Not comparable

GLM-5.3-Flash: 42.6 (#25), Reka Flash 3: —

BenchmarkGLM-5.3-FlashReka Flash 3
LMArena Vision1304—

Multilingual Not comparable

GLM-5.3-Flash: 56.2 (#24), Reka Flash 3: —

BenchmarkGLM-5.3-FlashReka Flash 3
LMArena Non-English1462—
LMArena Chinese1529—
LMArena French1495—
LMArena German1457—
LMArena Japanese1420—
LMArena Korean1443—
LMArena Russian1472—
LMArena Spanish1471—

Instruction Following Not comparable

GLM-5.3-Flash: 77.8 (#17), Reka Flash 3: —

BenchmarkGLM-5.3-FlashReka Flash 3
LMArena Instruction Following1480—

Long Context Not comparable

GLM-5.3-Flash: 45.3 (#41), Reka Flash 3: —

BenchmarkGLM-5.3-FlashReka Flash 3
LMArena Longer Query1479—

Writing & Preference GLM-5.3-Flash leads

GLM-5.3-Flash: 65.4 (#49), Reka Flash 3: 43.8

BenchmarkGLM-5.3-FlashReka Flash 3
LMArena Text1471—
LMArena Creative Writing1440—
EQ-Bench Creative Writing—1228
LMArena Multi-Turn1471—

Frequently asked questions

Is GLM-5.3-Flash better than Reka Flash 3?

GLM-5.3-Flash has enough public results to be ranked (#45); Reka Flash 3 does not yet, so treat this comparison as directional.

Which is cheaper, GLM-5.3-Flash or Reka Flash 3?

Reka Flash 3 is cheaper. It lists at $0.10 per million input tokens and $0.20 per million output tokens; GLM-5.3-Flash lists at $0.15 and $0.50.

Which has the bigger context window?

GLM-5.3-Flash does, with 1M tokens against 66K.

How many benchmarks do GLM-5.3-Flash and Reka Flash 3 share?

0 benchmarks have published results for both models. GLM-5.3-Flash has 36 scored results on Noometry and Reka Flash 3 has 2.

Related comparisons

Go deeper