Noometry

Model comparison

Claude 3 Haiku vs Grok 4.3

Grok 4.3 is the stronger model overall, scoring 43.6 to 25.7 on the Noometry Index.

Last verified . 25 shared benchmarks.

Claude 3 Haiku Anthropic

25.7

Rank #333 Confirmed

Grok 4.3 xAI

43.6

Rank #80 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Grok 4.3 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok 4.3 leads 45.8 to 9.2.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 93.3% for Grok 4.3.

Side by side

Claude 3 HaikuGrok 4.3
ProviderAnthropicxAI
Noometry Index25.743.6
Released2024-03-072026-04-17
WeightsProprietaryProprietary
Context window—1M
Max output—30K
Input $ / M tokens—$1.25
Output $ / M tokens—$2.50
Results tracked3740

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

Category by category

Coding Grok 4.3 leads

Claude 3 Haiku: 26.1 (#320), Grok 4.3: 41.3 (#117)

BenchmarkClaude 3 HaikuGrok 4.3
WeirdML9.8%49.9%
LMArena Coding11991415
LMArena WebDev—1357
SciCode—47.3%
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
ALE-Bench—944.17
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, Grok 4.3: 27.6 (#93)

BenchmarkClaude 3 HaikuGrok 4.3
GDP.pdf—8%
LMArena Search—1165
Vending-Bench 2—35.26

Reasoning Grok 4.3 leads

Claude 3 Haiku: 15.7 (#303), Grok 4.3: 34.9 (#60)

BenchmarkClaude 3 HaikuGrok 4.3
LMArena Hard Prompts11741397
DTBench50.1%90.7%
LMCA8.8%38.3%
Epoch Capabilities Index118.3149.13
ForecastBench53.260.3
Kagi LLM Benchmark34.2%—
NYT Connections (extended)—55.2%
CritPt—8%
Chess Puzzles—25%
WinoGrande74.2%—

Math Grok 4.3 leads

Claude 3 Haiku: 9.2 (#313), Grok 4.3: 45.8 (#60)

BenchmarkClaude 3 HaikuGrok 4.3
OTIS Mock AIME 2024-20251.8%93.3%
LMArena Math11881388
FrontierMath (Tiers 1-3)—42.8%
FrontierMath Tier 4—14.6%
ProofBench—11%
MATH Level 514.9%—

Knowledge Grok 4.3 leads

Claude 3 Haiku: 17.3 (#280), Grok 4.3: 52.5 (#57)

BenchmarkClaude 3 HaikuGrok 4.3
GPQA Diamond36.3%88.8%
LMArena Expert11481385
SimpleQA Verified—33.2%
Confabulations34.2%—
MMLU73.8%—

Multimodal Grok 4.3 leads

Claude 3 Haiku: 23.1 (#123), Grok 4.3: 31.6 (#96)

BenchmarkClaude 3 HaikuGrok 4.3
LMArena Vision9501231
Blueprint-Bench 2—0%
ScienceQA72%—

Multilingual Grok 4.3 leads

Claude 3 Haiku: 36.1 (#238), Grok 4.3: 50.7 (#114)

BenchmarkClaude 3 HaikuGrok 4.3
LMArena Non-English11781385
LMArena Chinese11551423
LMArena French11941412
LMArena German11741395
LMArena Japanese11021379
LMArena Korean11081357
LMArena Russian12041399
LMArena Spanish11651402

Instruction Following Grok 4.3 leads

Claude 3 Haiku: 61.5 (#242), Grok 4.3: 72.3 (#135)

BenchmarkClaude 3 HaikuGrok 4.3
LMArena Instruction Following11741366

Long Context Grok 4.3 leads

Claude 3 Haiku: 36.1 (#232), Grok 4.3: 42.5 (#118)

BenchmarkClaude 3 HaikuGrok 4.3
LMArena Longer Query11911393

Writing & Preference Grok 4.3 leads

Claude 3 Haiku: 29.8 (#286), Grok 4.3: 58.6 (#112)

BenchmarkClaude 3 HaikuGrok 4.3
LMArena Text11951397
LMArena Creative Writing11571380
LMArena Multi-Turn11901406
EQ-Bench Creative Writing717—
EQ-Bench 4—1075

Frequently asked questions

Is Claude 3 Haiku better than Grok 4.3?

Grok 4.3 is the stronger model overall, scoring 43.6 to 25.7 on the Noometry Index.

Is Claude 3 Haiku or Grok 4.3 better for coding?

Grok 4.3 scores higher on coding benchmarks: 41.3 versus 26.1 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Grok 4.3 share?

25 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Grok 4.3 has 40.

Related comparisons

Go deeper