Noometry

Model comparison

GLM-4.6 vs Nemotron 3 Ultra

Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 40.9 on the Noometry Index.

Last verified . 19 shared benchmarks.

GLM-4.6 Z.ai (Zhipu)

40.9

Rank #132 Confirmed

Nemotron 3 Ultra NVIDIA

44.7

Rank #71 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GLM-4.6 scores higher in 2 categories and Nemotron 3 Ultra in 6 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 39.6.
  • Both cost about the same: $0.60 input and $2.20 output per million tokens.
  • Nemotron 3 Ultra accepts more context: 262K tokens versus 205K.

Side by side

GLM-4.6Nemotron 3 Ultra
ProviderZ.ai (Zhipu)NVIDIA
Noometry Index40.944.7
Released2025-09-302026-06-04
WeightsOpenOpen
Context window205K262K
Max output131K128K
Input $ / M tokens$0.60$0.60
Output $ / M tokens$2.20$2.40
Results tracked2929

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

Category by category

Coding GLM-4.6 leads

GLM-4.6: 39.9 (#137), Nemotron 3 Ultra: 37.7 (#174)

BenchmarkGLM-4.6Nemotron 3 Ultra
SciCode38.4%40.3%
LMArena Coding14491468
FrontierCode—13.6%
SWE-bench Verified (bash only)55.4%—
LMArena WebDev1339—
WeirdML—43.5%
ALE-Bench340.82—

Agentic & Tool Use Not comparable

GLM-4.6: 32.1 (#60), Nemotron 3 Ultra: —

BenchmarkGLM-4.6Nemotron 3 Ultra
Terminal-Bench24.5%—
Berkeley Function Calling Leaderboard72.4%—

Reasoning Nemotron 3 Ultra leads

GLM-4.6: 23.1 (#168), Nemotron 3 Ultra: 30.3 (#78)

BenchmarkGLM-4.6Nemotron 3 Ultra
CritPt1.1%3.1%
LMArena Hard Prompts14401452
Kagi LLM Benchmark47.4%—
Chess Puzzles—12%
Mystery Game Puzzles—20%
DTBench—90.1%
LMCA—36.9%
Epoch Capabilities Index—146.2

Math GLM-4.6 leads

GLM-4.6: 36.4 (#115), Nemotron 3 Ultra: 34.4 (#160)

BenchmarkGLM-4.6Nemotron 3 Ultra
LMArena Math14311456
OTIS Mock AIME 2024-2025—86.7%
ProofBench—2%
FrontierMath (Feb 2025 set)3.8%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge Nemotron 3 Ultra leads

GLM-4.6: 39.6 (#118), Nemotron 3 Ultra: 52.5 (#56)

BenchmarkGLM-4.6Nemotron 3 Ultra
LMArena Expert14321472
GPQA Diamond—85.4%
Vectara Hallucination Rate9.5%—

Multilingual Too close to call

GLM-4.6: 53.6 (#62), Nemotron 3 Ultra: 53.7 (#61)

BenchmarkGLM-4.6Nemotron 3 Ultra
LMArena Non-English14261427
LMArena Chinese15001498
LMArena French14591475
LMArena German14471471
LMArena Korean14011387
LMArena Russian14181415
LMArena Spanish14361452
LMArena Japanese1394—

Instruction Following Too close to call

GLM-4.6: 74.5 (#93), Nemotron 3 Ultra: 74.9 (#84)

BenchmarkGLM-4.6Nemotron 3 Ultra
LMArena Instruction Following14101417

Long Context Too close to call

GLM-4.6: 43.4 (#91), Nemotron 3 Ultra: 43.9 (#77)

BenchmarkGLM-4.6Nemotron 3 Ultra
LMArena Longer Query14231437

Writing & Preference Nemotron 3 Ultra leads

GLM-4.6: 61.3 (#86), Nemotron 3 Ultra: 66.3 (#35)

BenchmarkGLM-4.6Nemotron 3 Ultra
LMArena Text14401444
LMArena Creative Writing14111392
EQ-Bench Creative Writing14111692
LMArena Multi-Turn14271412

Frequently asked questions

Is GLM-4.6 better than Nemotron 3 Ultra?

Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 40.9 on the Noometry Index.

Which is cheaper, GLM-4.6 or Nemotron 3 Ultra?

GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Nemotron 3 Ultra lists at $0.60 and $2.40.

Is GLM-4.6 or Nemotron 3 Ultra better for coding?

GLM-4.6 scores higher on coding benchmarks: 39.9 versus 37.7 in the Noometry coding category.

Which has the bigger context window?

Nemotron 3 Ultra does, with 262K tokens against 205K.

How many benchmarks do GLM-4.6 and Nemotron 3 Ultra share?

19 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Nemotron 3 Ultra has 29.

Related comparisons

Go deeper