Noometry

Model comparison

Claude 3 Haiku vs Kimi K2.7 Code

Kimi K2.7 Code is the stronger model overall, scoring 43.0 to 25.7 on the Noometry Index.

Last verified . 4 shared benchmarks.

Claude 3 Haiku Anthropic

25.7

Rank #333 Confirmed

Kimi K2.7 Code Moonshot AI

43.0

Rank #90 Confirmed

Summary

  • They share 4 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Kimi K2.7 Code in 4 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K2.7 Code leads 52.6 to 9.2.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 95.6% for Kimi K2.7 Code.
  • Kimi K2.7 Code has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuKimi K2.7 Code
ProviderAnthropicMoonshot AI
Noometry Index25.743.0
Released2024-03-072026-06-12
WeightsProprietaryOpen
Context window—262K
Max output—262K
Input $ / M tokens—$0.95
Output $ / M tokens—$4
Results tracked3719

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

Category by category

Coding Kimi K2.7 Code leads

Claude 3 Haiku: 26.1 (#320), Kimi K2.7 Code: 42.4 (#92)

BenchmarkClaude 3 HaikuKimi K2.7 Code
WeirdML9.8%54.1%
DeepSWE—30.5%
FrontierCode—30.1%
LMArena WebDev—1473
SciCode—47.5%
BigCodeBench Instruct39.4%—
LMArena Coding1199—
BigCodeBench Complete50.1%—
CadEval12%—
ALE-Bench—886.23
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, Kimi K2.7 Code: 23.9 (#115)

BenchmarkClaude 3 HaikuKimi K2.7 Code
APEX-Agents—37.6%
GBAEval—0.9%
Vending-Bench 2—5,083

Reasoning Kimi K2.7 Code leads

Claude 3 Haiku: 15.7 (#303), Kimi K2.7 Code: 38.2 (#56)

BenchmarkClaude 3 HaikuKimi K2.7 Code
Epoch Capabilities Index118.3150.01
SimpleBench—57.9%
Kagi LLM Benchmark34.2%—
CritPt—10%
Chess Puzzles—21%
LMArena Hard Prompts1174—
DTBench50.1%—
LMCA8.8%—
Surface Evolver Bench—48.8%
ForecastBench53.2—
WinoGrande74.2%—

Math Kimi K2.7 Code leads

Claude 3 Haiku: 9.2 (#313), Kimi K2.7 Code: 52.6 (#39)

BenchmarkClaude 3 HaikuKimi K2.7 Code
OTIS Mock AIME 2024-20251.8%95.6%
FrontierMath (Tiers 1-3)—54%
FrontierMath Tier 4—12.2%
LMArena Math1188—
MATH Level 514.9%—

Knowledge Kimi K2.7 Code leads

Claude 3 Haiku: 17.3 (#280), Kimi K2.7 Code: 53.6 (#51)

BenchmarkClaude 3 HaikuKimi K2.7 Code
GPQA Diamond36.3%87.9%
SimpleQA Verified—36.5%
Confabulations34.2%—
LMArena Expert1148—
MMLU73.8%—

Multimodal Not comparable

Claude 3 Haiku: 23.1 (#123), Kimi K2.7 Code: —

BenchmarkClaude 3 HaikuKimi K2.7 Code
LMArena Vision950—
ScienceQA72%—

Multilingual Not comparable

Claude 3 Haiku: 36.1 (#238), Kimi K2.7 Code: —

BenchmarkClaude 3 HaikuKimi K2.7 Code
LMArena Non-English1178—
LMArena Chinese1155—
LMArena French1194—
LMArena German1174—
LMArena Japanese1102—
LMArena Korean1108—
LMArena Russian1204—
LMArena Spanish1165—

Instruction Following Not comparable

Claude 3 Haiku: 61.5 (#242), Kimi K2.7 Code: —

BenchmarkClaude 3 HaikuKimi K2.7 Code
LMArena Instruction Following1174—

Long Context Not comparable

Claude 3 Haiku: 36.1 (#232), Kimi K2.7 Code: —

BenchmarkClaude 3 HaikuKimi K2.7 Code
LMArena Longer Query1191—

Writing & Preference Not comparable

Claude 3 Haiku: 29.8 (#286), Kimi K2.7 Code: —

BenchmarkClaude 3 HaikuKimi K2.7 Code
LMArena Text1195—
LMArena Creative Writing1157—
EQ-Bench Creative Writing717—
LMArena Multi-Turn1190—

Frequently asked questions

Is Claude 3 Haiku better than Kimi K2.7 Code?

Kimi K2.7 Code is the stronger model overall, scoring 43.0 to 25.7 on the Noometry Index.

Is Claude 3 Haiku or Kimi K2.7 Code better for coding?

Kimi K2.7 Code scores higher on coding benchmarks: 42.4 versus 26.1 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Kimi K2.7 Code share?

4 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Kimi K2.7 Code has 19.

Related comparisons

Go deeper