Noometry

Model comparison

Claude 3.5 Haiku vs Grok 4

Grok 4 is the stronger model overall, scoring 47.8 to 28.9 on the Noometry Index.

Last verified . 33 shared benchmarks.

Claude 3.5 Haiku Anthropic

28.9

Rank #309 Confirmed

Grok 4 xAI

47.8

Rank #49 Confirmed

Summary

  • They share 33 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and Grok 4 in 10 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok 4 leads 53.7 to 18.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.3% for Claude 3.5 Haiku and 84% for Grok 4.

Side by side

Claude 3.5 HaikuGrok 4
ProviderAnthropicxAI
Noometry Index28.947.8
Released2024-10-222025-07-09
WeightsProprietaryProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4948

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

Category by category

Coding Grok 4 leads

Claude 3.5 Haiku: 32.6 (#258), Grok 4: 49.9 (#44)

BenchmarkClaude 3.5 HaikuGrok 4
Aider Polyglot28%79.6%
WeirdML30.7%45.7%
LMArena Coding12871408
SciCode27.4%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
BigCodeBench Complete59%—
CadEval32%—

Agentic & Tool Use Grok 4 leads

Claude 3.5 Haiku: 27.7 (#90), Grok 4: 32.1 (#62)

BenchmarkClaude 3.5 HaikuGrok 4
BALROG19.3%43.6%
Terminal-Bench—27.2%
Berkeley Function Calling Leaderboard—63%
GDPval—21.1%
Cybench—43%
DeepResearch Bench—47.3%
LMArena Search—1142
METR Time Horizons—66.6%

Reasoning Grok 4 leads

Claude 3.5 Haiku: 17.1 (#286), Grok 4: 36.9 (#59)

BenchmarkClaude 3.5 HaikuGrok 4
LMArena Hard Prompts12511409
Epoch Capabilities Index127.15146.46
ARC-AGI-2—16%
SimpleBench—60.5%
Kagi LLM Benchmark—73.6%
ARC-AGI-1—66.7%
CritPt0%—
Chess Puzzles—28%
LiveBench Reasoning28.1%—
DTBench56.7%—
LiveBench Data Analysis48.5%—
ForecastBench—60.9
LiveBench43.5%—

Math Grok 4 leads

Claude 3.5 Haiku: 13.7 (#294), Grok 4: 46.5 (#58)

BenchmarkClaude 3.5 HaikuGrok 4
OTIS Mock AIME 2024-20254.3%84%
Omni-MATH22.4%60.3%
LMArena Math12441422
FrontierMath (Feb 2025 set)0.3%19.7%
LiveBench Math35.5%—
MATH Level 546.4%—
FrontierMath Tier 4 (v1)—2.1%

Knowledge Grok 4 leads

Claude 3.5 Haiku: 18.7 (#276), Grok 4: 53.7 (#50)

BenchmarkClaude 3.5 HaikuGrok 4
GPQA Diamond38.1%87%
MMLU-Pro60.5%85.1%
Confabulations36.7%12.4%
GPQA (HELM)36.3%72.7%
LMArena Expert12081417
MMLU74.3%—

Multimodal Grok 4 leads

Claude 3.5 Haiku: 26.3 (#113), Grok 4: 33.1 (#89)

BenchmarkClaude 3.5 HaikuGrok 4
LMArena Vision10921211
GeoBench34%45%

Multilingual Grok 4 leads

Claude 3.5 Haiku: 40.2 (#213), Grok 4: 52.0 (#98)

BenchmarkClaude 3.5 HaikuGrok 4
LMArena Non-English12381403
LMArena Chinese12291428
LMArena French12621418
LMArena German12371429
LMArena Japanese11751396
LMArena Korean11721376
LMArena Russian12531409
LMArena Spanish12611419

Instruction Following Grok 4 leads

Claude 3.5 Haiku: 63.1 (#229), Grok 4: 79.4 (#4)

BenchmarkClaude 3.5 HaikuGrok 4
IFEval79.2%94.9%
LMArena Instruction Following12411387
LiveBench Instruction Following61.9%—

Long Context Grok 4 leads

Claude 3.5 Haiku: 38.3 (#195), Grok 4: 63.1 (#4)

BenchmarkClaude 3.5 HaikuGrok 4
LMArena Longer Query12611409
Fiction.LiveBench—94.4%

Writing & Preference Grok 4 leads

Claude 3.5 Haiku: 42.9 (#228), Grok 4: 58.7 (#111)

BenchmarkClaude 3.5 HaikuGrok 4
LMArena Text12551412
LMArena Creative Writing12331397
Short-Story Creative Writing73.5%76.9%
WildBench76%79.7%
LMArena Multi-Turn12651416
EQ-Bench Creative Writing1146—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than Grok 4?

Grok 4 is the stronger model overall, scoring 47.8 to 28.9 on the Noometry Index.

Is Claude 3.5 Haiku or Grok 4 better for coding?

Grok 4 scores higher on coding benchmarks: 49.9 versus 32.6 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and Grok 4 share?

33 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Grok 4 has 48.

Related comparisons

Go deeper