Model comparison

Kimi K3 vs Nemotron-4 15B

Kimi K3 has enough public results to be ranked (#15); Nemotron-4 15B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

Kimi K3 Moonshot AI

59.5

Rank #15 Confirmed

Nemotron-4 15B NVIDIA

—

Unranked

Summary

  • They share 1 benchmark with published results for both.
  • Kimi K3 has downloadable open weights; the other is API-only.

Side by side

Kimi K3 and Nemotron-4 15B specifications
Kimi K3Nemotron-4 15B
ProviderMoonshot AINVIDIA
Noometry Index59.5—
Released2026-07-162024-02-26
WeightsOpenProprietary
Context window1.05M—
Max output1.05M—
Input $ / M tokens$3—
Output $ / M tokens$15—
Results tracked538

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

Category by category

Coding Not comparable

Kimi K3: 61.0 (#10), Nemotron-4 15B: —

Coding benchmarks
BenchmarkKimi K3Nemotron-4 15B
DeepSWE68.5%—
FrontierCode44.2%—
LMArena WebDev1654—
FrontierSWE25.9%—
SciCode59.5%—
WeirdML82.6%—
LMArena Coding1508—
ALE-Bench1,524—

Agentic & Tool Use Not comparable

Kimi K3: 41.8 (#20), Nemotron-4 15B: —

Agentic & Tool Use benchmarks
BenchmarkKimi K3Nemotron-4 15B
APEX-Agents50.6%—
τ²-bench Banking37.1%—
PostTrainBench32%—
GBAEval48.3%—
GDP.pdf19%—
Vending-Bench 25,165—

Reasoning Not comparable

Kimi K3: 63.0 (#17), Nemotron-4 15B: —

Reasoning benchmarks
BenchmarkKimi K3Nemotron-4 15B
Epoch Capabilities Index157.45107.72
ARC-AGI-260.4%—
SimpleBench60.7%—
NYT Connections (extended)93.6%—
ARC-AGI-194.5%—
CritPt23.4%—
Chess Puzzles39%—
LMArena Hard Prompts1496—
Mystery Game Puzzles26%—
DTBench91.2%—
LMCA52.7%—
Surface Evolver Bench95%—
BIG-Bench Hard—58.7%
ForecastBench61.1—
HellaSwag—82.4%
PIQA—82.4%
WinoGrande—78%

Math Not comparable

Kimi K3: 74.2 (#16), Nemotron-4 15B: —

Math benchmarks
BenchmarkKimi K3Nemotron-4 15B
FrontierMath (Tiers 1-3)72.2%—
FrontierMath Tier 439%—
MathArena Final-Answer Competitions87.8%—
OTIS Mock AIME 2024-202597.2%—
ProofBench87%—
LMArena Math1491—
GSM8K—46%

Knowledge Not comparable

Kimi K3: 63.2 (#21), Nemotron-4 15B: —

Knowledge benchmarks
BenchmarkKimi K3Nemotron-4 15B
GPQA Diamond93.1%—
SimpleQA Verified50.6%—
LMArena Expert1521—
ARC (AI2) Challenge—55.5%
MMLU—58.7%

Multimodal Not comparable

Kimi K3: 37.8 (#70), Nemotron-4 15B: —

Multimodal benchmarks
BenchmarkKimi K3Nemotron-4 15B
Blueprint-Bench 229.5%—
Furniture Assembly34.2%—

Multilingual Not comparable

Kimi K3: 56.3 (#21), Nemotron-4 15B: —

Multilingual benchmarks
BenchmarkKimi K3Nemotron-4 15B
LMArena Non-English1466—
LMArena Chinese1529—
LMArena French1491—
LMArena German1488—
LMArena Japanese1487—
LMArena Korean1458—
LMArena Russian1482—
LMArena Spanish1472—

Instruction Following Not comparable

Kimi K3: 77.7 (#14), Nemotron-4 15B: —

Instruction Following benchmarks
BenchmarkKimi K3Nemotron-4 15B
LMArena Instruction Following1483—

Long Context Not comparable

Kimi K3: 45.8 (#29), Nemotron-4 15B: —

Long Context benchmarks
BenchmarkKimi K3Nemotron-4 15B
LMArena Longer Query1494—

Writing & Preference Not comparable

Kimi K3: 76.6 (#4), Nemotron-4 15B: —

Writing & Preference benchmarks
BenchmarkKimi K3Nemotron-4 15B
LMArena Text1476—
LMArena Creative Writing1454—
EQ-Bench Creative Writing2082—
EQ-Bench 41339—
LMArena Multi-Turn1488—

Frequently asked questions

Is Kimi K3 better than Nemotron-4 15B?

Kimi K3 has enough public results to be ranked (#15); Nemotron-4 15B does not yet, so treat this comparison as directional.

How many benchmarks do Kimi K3 and Nemotron-4 15B share?

1 benchmark has published results for both models. Kimi K3 has 53 scored results on Noometry and Nemotron-4 15B has 8.

Related comparisons

Go deeper