Noometry

Model comparison

Claude 3.5 Haiku vs Grok-3 mini

Grok-3 mini is the stronger model overall, scoring 41.2 to 29.2 on the Noometry Index.

Last verified . 31 shared benchmarks.

Claude 3.5 Haiku Anthropic

29.2

Rank #315 Confirmed

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Summary

  • They share 31 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 1 category and Grok-3 mini in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok-3 mini leads 46.4 to 18.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.3% for Claude 3.5 Haiku and 77.8% for Grok-3 mini.

Side by side

Claude 3.5 HaikuGrok-3 mini
ProviderAnthropicxAI
Noometry Index29.241.2
Released2024-10-222025-04-09
WeightsProprietaryProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4935

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

Category by category

Coding Grok-3 mini leads

Claude 3.5 Haiku: 32.9 (#265), Grok-3 mini: 40.8 (#131)

BenchmarkClaude 3.5 HaikuGrok-3 mini
Aider Polyglot28%49.3%
WeirdML30.7%42.6%
LMArena Coding12861379
SciCode27.4%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
BigCodeBench Complete59%—
CadEval32%—

Agentic & Tool Use Not comparable

Claude 3.5 Haiku: 28.0 (#95), Grok-3 mini: —

BenchmarkClaude 3.5 HaikuGrok-3 mini
BALROG19.3%—

Reasoning Claude 3.5 Haiku leads

Claude 3.5 Haiku: 17.7 (#290), Grok-3 mini: 13.6 (#334)

BenchmarkClaude 3.5 HaikuGrok-3 mini
LMArena Hard Prompts12511375
Epoch Capabilities Index127.15140.35
ARC-AGI-2—0.4%
Kagi LLM Benchmark—61.3%
ARC-AGI-1—16.5%
CritPt0%—
LiveBench Reasoning28.1%—
DTBench56.7%—
LiveBench Data Analysis48.5%—
LiveBench43.5%—

Math Grok-3 mini leads

Claude 3.5 Haiku: 14.7 (#300), Grok-3 mini: 42.1 (#85)

BenchmarkClaude 3.5 HaikuGrok-3 mini
OTIS Mock AIME 2024-20254.3%77.8%
Omni-MATH22.4%31.8%
LMArena Math12441386
MATH Level 546.4%90.9%
FrontierMath (Feb 2025 set)0.3%5.9%
LiveBench Math35.5%—

Knowledge Grok-3 mini leads

Claude 3.5 Haiku: 18.7 (#281), Grok-3 mini: 46.4 (#81)

BenchmarkClaude 3.5 HaikuGrok-3 mini
GPQA Diamond38.1%76.3%
MMLU-Pro60.5%79.9%
Confabulations36.7%10.8%
GPQA (HELM)36.3%67.5%
LMArena Expert12081395
MMLU74.3%—

Multimodal Not comparable

Claude 3.5 Haiku: 26.8 (#117), Grok-3 mini: —

BenchmarkClaude 3.5 HaikuGrok-3 mini
LMArena Vision1092—
GeoBench34%—

Multilingual Grok-3 mini leads

Claude 3.5 Haiku: 40.0 (#218), Grok-3 mini: 48.1 (#145)

BenchmarkClaude 3.5 HaikuGrok-3 mini
LMArena Non-English12381352
LMArena Chinese12291387
LMArena French12641357
LMArena German12371349
LMArena Japanese11751342
LMArena Korean11731335
LMArena Russian12531353
LMArena Spanish12611381

Instruction Following Grok-3 mini leads

Claude 3.5 Haiku: 62.9 (#234), Grok-3 mini: 78.5 (#9)

BenchmarkClaude 3.5 HaikuGrok-3 mini
IFEval79.2%95.1%
LMArena Instruction Following12411357
LiveBench Instruction Following61.9%—

Long Context Grok-3 mini leads

Claude 3.5 Haiku: 38.3 (#200), Grok-3 mini: 41.0 (#147)

BenchmarkClaude 3.5 HaikuGrok-3 mini
LMArena Longer Query12611372
Fiction.LiveBench—66.7%

Writing & Preference Grok-3 mini leads

Claude 3.5 Haiku: 42.7 (#234), Grok-3 mini: 52.5 (#169)

BenchmarkClaude 3.5 HaikuGrok-3 mini
LMArena Text12551370
LMArena Creative Writing12331342
Short-Story Creative Writing73.5%73.5%
WildBench76%65.1%
LMArena Multi-Turn12651355
EQ-Bench Creative Writing1146—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than Grok-3 mini?

Grok-3 mini is the stronger model overall, scoring 41.2 to 29.2 on the Noometry Index.

Is Claude 3.5 Haiku or Grok-3 mini better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and Grok-3 mini share?

31 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Grok-3 mini has 35.

Related comparisons

Go deeper