Noometry

Model comparison

Kimi K2.6 vs Qwen2-72B

Kimi K2.6 is the stronger model overall, scoring 47.7 to 30.0 on the Noometry Index.

Last verified . 20 shared benchmarks.

Kimi K2.6 Moonshot AI

47.7

Rank #60 Confirmed

Qwen2-72B Alibaba (Qwen)

30.0

Rank #300 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Kimi K2.6 scores higher in 9 categories and Qwen2-72B in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Kimi K2.6 leads 54.0 to 21.2.
  • The biggest single-benchmark swing is GPQA Diamond: 90.8% for Kimi K2.6 and 40.8% for Qwen2-72B.

Side by side

Kimi K2.6Qwen2-72B
ProviderMoonshot AIAlibaba (Qwen)
Noometry Index47.730.0
Released2026-04-202024-06-07
WeightsOpenOpen
Context window262K—
Max output262K—
Input $ / M tokens$0.95—
Output $ / M tokens$4—
Results tracked5126

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

Category by category

Coding Kimi K2.6 leads

Kimi K2.6: 50.7 (#43), Qwen2-72B: 29.1 (#310)

BenchmarkKimi K2.6Qwen2-72B
WeirdML55.9%11.3%
LMArena Coding14881196
SWE-bench Verified76.7%—
LMArena WebDev1509—
SciCode53.5%—
BigCodeBench Instruct—38.5%
BigCodeBench Complete—54%
ALE-Bench1,093—

Agentic & Tool Use Kimi K2.6 leads

Kimi K2.6: 21.9 (#137), Qwen2-72B: 17.0 (#146)

BenchmarkKimi K2.6Qwen2-72B
OSWorld 2.04.6%—
TheAgentCompany—1.1%
ExploitBench18.4%—
GBAEval0.9%—
GDP.pdf12%—
METR Time Horizons—29.9%
Vending-Bench 26,205—

Reasoning Kimi K2.6 leads

Kimi K2.6: 40.5 (#55), Qwen2-72B: 23.2 (#181)

BenchmarkKimi K2.6Qwen2-72B
LMArena Hard Prompts14701191
Epoch Capabilities Index151.05125.28
NYT Connections (extended)87.2%—
CritPt8%—
Chess Puzzles26%—
EBR-Bench2.4%—
Mystery Game Puzzles18%—
DTBench90.9%—
LMCA37.3%—

Math Kimi K2.6 leads

Kimi K2.6: 57.0 (#41), Qwen2-72B: 30.2 (#236)

BenchmarkKimi K2.6Qwen2-72B
LMArena Math14751235
FrontierMath (Tiers 1-3)57.2%—
FrontierMath Tier 425.6%—
MathArena Final-Answer Competitions72.9%—
OTIS Mock AIME 2024-202596.1%—
ProofBench16%—
MATH Level 5—39.1%
FrontierMath (Feb 2025 set)39%—
FrontierMath Tier 4 (v1)14.6%—

Knowledge Kimi K2.6 leads

Kimi K2.6: 54.0 (#54), Qwen2-72B: 21.2 (#275)

BenchmarkKimi K2.6Qwen2-72B
GPQA Diamond90.8%40.8%
LMArena Expert14911171
SimpleQA Verified34.9%—
Vectara Hallucination Rate10.8%—
MMLU—82.4%

Multimodal Not comparable

Kimi K2.6: 31.6 (#103), Qwen2-72B: —

BenchmarkKimi K2.6Qwen2-72B
LMArena Vision1283—
Blueprint-Bench 23.9%—
Furniture Assembly21.7%—
LMArena Document1451—

Multilingual Kimi K2.6 leads

Kimi K2.6: 54.9 (#37), Qwen2-72B: 35.9 (#244)

BenchmarkKimi K2.6Qwen2-72B
LMArena Non-English14461176
LMArena Chinese15211240
LMArena French14711170
LMArena German14501151
LMArena Japanese14431111
LMArena Korean14271083
LMArena Russian14461169
LMArena Spanish14641169

Instruction Following Kimi K2.6 leads

Kimi K2.6: 76.3 (#43), Qwen2-72B: 61.7 (#241)

BenchmarkKimi K2.6Qwen2-72B
LMArena Instruction Following14511181

Long Context Kimi K2.6 leads

Kimi K2.6: 44.9 (#52), Qwen2-72B: 36.1 (#235)

BenchmarkKimi K2.6Qwen2-72B
LMArena Longer Query14681192

Writing & Preference Kimi K2.6 leads

Kimi K2.6: 68.5 (#26), Qwen2-72B: 40.8 (#241)

BenchmarkKimi K2.6Qwen2-72B
LMArena Text14551203
LMArena Creative Writing14341181
LMArena Multi-Turn14531196
EQ-Bench Creative Writing1725—
EQ-Bench 41202—

Frequently asked questions

Is Kimi K2.6 better than Qwen2-72B?

Kimi K2.6 is the stronger model overall, scoring 47.7 to 30.0 on the Noometry Index.

Is Kimi K2.6 or Qwen2-72B better for coding?

Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 29.1 in the Noometry coding category.

How many benchmarks do Kimi K2.6 and Qwen2-72B share?

20 benchmarks have published results for both models. Kimi K2.6 has 51 scored results on Noometry and Qwen2-72B has 26.

Related comparisons

Go deeper