Noometry

Model comparison

gpt-oss-20b vs Kimi K2 Thinking Turbo

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 32.5 on the Noometry Index.

Last verified . 19 shared benchmarks.

gpt-oss-20b OpenAI

32.5

Rank #255 Confirmed

Kimi K2 Thinking Turbo Moonshot AI

45.8

Rank #70 Confirmed

Summary

  • They share 19 benchmarks with published results for both. gpt-oss-20b scores higher in 0 categories and Kimi K2 Thinking Turbo in 8 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Kimi K2 Thinking Turbo leads 60.0 to 35.5.
  • The biggest single-benchmark swing is GPQA Diamond: 60.8% for gpt-oss-20b and 84.2% for Kimi K2 Thinking Turbo.

Side by side

gpt-oss-20bKimi K2 Thinking Turbo
ProviderOpenAIMoonshot AI
Noometry Index32.545.8
Released2025-08-052025-11-06
WeightsOpenOpen
Context window131K—
Max output16K—
Input $ / M tokens$0.018—
Output $ / M tokens$0.09—
Results tracked3421

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

Category by category

Coding Too close to call

gpt-oss-20b: 37.6 (#192), Kimi K2 Thinking Turbo: 38.4 (#178)

Benchmarkgpt-oss-20bKimi K2 Thinking Turbo
LMArena Coding13061454
LMArena WebDev—1322
SciCode34.4%—
WeirdML40.9%—
ALE-Bench566.05—

Agentic & Tool Use Not comparable

gpt-oss-20b: 9.3 (#154), Kimi K2 Thinking Turbo: —

Benchmarkgpt-oss-20bKimi K2 Thinking Turbo
Terminal-Bench3.4%—

Reasoning Kimi K2 Thinking Turbo leads

gpt-oss-20b: 19.3 (#261), Kimi K2 Thinking Turbo: 32.5 (#75)

Benchmarkgpt-oss-20bKimi K2 Thinking Turbo
Chess Puzzles4%20%
LMArena Hard Prompts12741428
Kagi LLM Benchmark53.2%—
CritPt1.4%—
DTBench68%—
LMCA14.5%—
Epoch Capabilities Index137.82—

Math Kimi K2 Thinking Turbo leads

gpt-oss-20b: 39.4 (#103), Kimi K2 Thinking Turbo: 47.4 (#68)

Benchmarkgpt-oss-20bKimi K2 Thinking Turbo
OTIS Mock AIME 2024-202565.3%83.1%
LMArena Math13171429
Omni-MATH56.5%—

Knowledge Kimi K2 Thinking Turbo leads

gpt-oss-20b: 34.6 (#195), Kimi K2 Thinking Turbo: 50.9 (#69)

Benchmarkgpt-oss-20bKimi K2 Thinking Turbo
GPQA Diamond60.8%84.2%
LMArena Expert12581439
MMLU-Pro74%—
GPQA (HELM)59.4%—

Multilingual Kimi K2 Thinking Turbo leads

gpt-oss-20b: 42.2 (#197), Kimi K2 Thinking Turbo: 51.4 (#109)

Benchmarkgpt-oss-20bKimi K2 Thinking Turbo
LMArena Non-English12681398
LMArena Chinese13141456
LMArena German12551390
LMArena Japanese12441357
LMArena Korean12361330
LMArena Russian12781391
LMArena Spanish12671406
LMArena French—1425

Instruction Following Kimi K2 Thinking Turbo leads

gpt-oss-20b: 61.8 (#240), Kimi K2 Thinking Turbo: 74.0 (#109)

Benchmarkgpt-oss-20bKimi K2 Thinking Turbo
LMArena Instruction Following12361403
IFEval73.2%—

Long Context Kimi K2 Thinking Turbo leads

gpt-oss-20b: 37.9 (#209), Kimi K2 Thinking Turbo: 43.2 (#102)

Benchmarkgpt-oss-20bKimi K2 Thinking Turbo
LMArena Longer Query12501415

Writing & Preference Kimi K2 Thinking Turbo leads

gpt-oss-20b: 35.5 (#265), Kimi K2 Thinking Turbo: 60.0 (#104)

Benchmarkgpt-oss-20bKimi K2 Thinking Turbo
LMArena Text12871415
LMArena Creative Writing12011374
LMArena Multi-Turn12681414
EQ-Bench Creative Writing666—
WildBench73.7%—

Frequently asked questions

Is gpt-oss-20b better than Kimi K2 Thinking Turbo?

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 32.5 on the Noometry Index.

Is gpt-oss-20b or Kimi K2 Thinking Turbo better for coding?

They score almost the same on coding (37.6 vs 38.4); test both on your own repository before choosing.

How many benchmarks do gpt-oss-20b and Kimi K2 Thinking Turbo share?

19 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Kimi K2 Thinking Turbo has 21.

Related comparisons

Go deeper