Noometry

Model comparison

Kimi K2.7 Code vs Llama 2-7B

Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 29.1 on the Noometry Index.

Last verified . 2 shared benchmarks.

Kimi K2.7 Code Moonshot AI

43.3

Rank #94 Confirmed

Llama 2-7B Meta

29.1

Rank #317 Confirmed

Summary

  • They share 2 benchmarks with published results for both. Kimi K2.7 Code scores higher in 4 categories and Llama 2-7B in 0 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Kimi K2.7 Code leads 53.5 to 28.2.
  • The biggest single-benchmark swing is Chess Puzzles: 21% for Kimi K2.7 Code and 0% for Llama 2-7B.

Side by side

Kimi K2.7 CodeLlama 2-7B
ProviderMoonshot AIMeta
Noometry Index43.329.1
Released2026-06-122023-07-18
WeightsOpenOpen
Context window262K—
Max output262K—
Input $ / M tokens$0.95—
Output $ / M tokens$4—
Results tracked1929

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

Category by category

Coding Kimi K2.7 Code leads

Kimi K2.7 Code: 42.9 (#95), Llama 2-7B: 29.2 (#307)

BenchmarkKimi K2.7 CodeLlama 2-7B
DeepSWE30.5%—
FrontierCode30.1%—
LMArena WebDev1473—
SciCode47.5%—
WeirdML54.1%—
LMArena Coding—1002
ALE-Bench886.23—

Agentic & Tool Use Not comparable

Kimi K2.7 Code: 24.0 (#122), Llama 2-7B: —

BenchmarkKimi K2.7 CodeLlama 2-7B
APEX-Agents37.6%—
GBAEval0.9%—
Vending-Bench 25,083—

Reasoning Kimi K2.7 Code leads

Kimi K2.7 Code: 39.0 (#61), Llama 2-7B: 15.7 (#312)

BenchmarkKimi K2.7 CodeLlama 2-7B
Chess Puzzles21%0%
Epoch Capabilities Index149.9799.06
SimpleBench57.9%—
CritPt10%—
LMArena Hard Prompts—1009
Surface Evolver Bench48.8%—
BIG-Bench Hard—39.2%
HellaSwag—77.2%
LAMBADA—73.3%
PIQA—78.8%
WinoGrande—69.2%

Math Kimi K2.7 Code leads

Kimi K2.7 Code: 52.9 (#48), Llama 2-7B: 30.7 (#233)

BenchmarkKimi K2.7 CodeLlama 2-7B
FrontierMath (Tiers 1-3)54%—
FrontierMath Tier 412.2%—
OTIS Mock AIME 2024-202595.6%—
LMArena Math—1042
GSM8K—16.7%

Knowledge Kimi K2.7 Code leads

Kimi K2.7 Code: 53.5 (#57), Llama 2-7B: 28.2 (#248)

BenchmarkKimi K2.7 CodeLlama 2-7B
GPQA Diamond87.9%—
SimpleQA Verified36.5%—
LMArena Expert—1036
ARC (AI2) Challenge—45.9%
BoolQ—77.9%
MMLU—45.8%
OpenBookQA—58.6%
TriviaQA—73.7%

Multimodal Not comparable

Kimi K2.7 Code: —, Llama 2-7B: —

BenchmarkKimi K2.7 CodeLlama 2-7B
ScienceQA—43.1%

Multilingual Not comparable

Kimi K2.7 Code: —, Llama 2-7B: 23.8 (#293)

BenchmarkKimi K2.7 CodeLlama 2-7B
LMArena Non-English—973
LMArena Chinese—973
LMArena French—970
LMArena German—978
LMArena Russian—995
LMArena Spanish—1007

Instruction Following Not comparable

Kimi K2.7 Code: —, Llama 2-7B: 50.8 (#298)

BenchmarkKimi K2.7 CodeLlama 2-7B
LMArena Instruction Following—1006

Long Context Not comparable

Kimi K2.7 Code: —, Llama 2-7B: 30.4 (#287)

BenchmarkKimi K2.7 CodeLlama 2-7B
LMArena Longer Query—999

Writing & Preference Not comparable

Kimi K2.7 Code: —, Llama 2-7B: 28.0 (#298)

BenchmarkKimi K2.7 CodeLlama 2-7B
LMArena Text—1053
LMArena Creative Writing—1033
LMArena Multi-Turn—1029

Frequently asked questions

Is Kimi K2.7 Code better than Llama 2-7B?

Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 29.1 on the Noometry Index.

Is Kimi K2.7 Code or Llama 2-7B better for coding?

Kimi K2.7 Code scores higher on coding benchmarks: 42.9 versus 29.2 in the Noometry coding category.

How many benchmarks do Kimi K2.7 Code and Llama 2-7B share?

2 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and Llama 2-7B has 29.

Related comparisons

Go deeper