Noometry

Model comparison

Claude 3 Haiku vs Grok 4.7

Grok 4.7 is the stronger model overall, scoring 53.1 to 25.9 on the Noometry Index.

Last verified . 21 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Grok 4.7 xAI

53.1

Rank #37 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Grok 4.7 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok 4.7 leads 57.8 to 9.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 98.1% for Grok 4.7.

Side by side

Claude 3 HaikuGrok 4.7
ProviderAnthropicxAI
Noometry Index25.953.1
Released2024-03-072026-09-21
WeightsProprietaryProprietary
Context window—500K
Max output—500K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked3739

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

Category by category

Coding Grok 4.7 leads

Claude 3 Haiku: 26.4 (#325), Grok 4.7: 58.0 (#18)

BenchmarkClaude 3 HaikuGrok 4.7
LMArena Coding11991427
FrontierCode—47.6%
CursorBench—46.3%
LMArena WebDev—1639
FrontierSWE—29.5%
SciCode—57.8%
WeirdML9.8%—
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, Grok 4.7: 36.7 (#37)

BenchmarkClaude 3 HaikuGrok 4.7
APEX-Agents—54.6%
GDP.pdf—22.8%
Vending-Bench 2—10,537

Reasoning Grok 4.7 leads

Claude 3 Haiku: 16.3 (#307), Grok 4.7: 49.1 (#40)

BenchmarkClaude 3 HaikuGrok 4.7
LMArena Hard Prompts11741413
DTBench50.1%96%
LMCA8.8%49.4%
Epoch Capabilities Index118.35153.53
Kagi LLM Benchmark34.2%—
NYT Connections (extended)—76.8%
CritPt—18%
Chess Puzzles—38%
Mystery Game Puzzles—29%
ForecastBench53.2—
WinoGrande74.2%—

Math Grok 4.7 leads

Claude 3 Haiku: 9.8 (#319), Grok 4.7: 57.8 (#39)

BenchmarkClaude 3 HaikuGrok 4.7
OTIS Mock AIME 2024-20251.8%98.1%
LMArena Math11881407
FrontierMath (Tiers 1-3)—53%
FrontierMath Tier 4—17.1%
ProofBench—34%
MATH Level 514.9%—

Knowledge Grok 4.7 leads

Claude 3 Haiku: 17.3 (#285), Grok 4.7: 62.8 (#22)

BenchmarkClaude 3 HaikuGrok 4.7
GPQA Diamond36.3%92.7%
LMArena Expert11481422
SimpleQA Verified—56%
Confabulations34.2%—
MMLU73.8%—

Multimodal Grok 4.7 leads

Claude 3 Haiku: 23.6 (#128), Grok 4.7: 35.5 (#87)

BenchmarkClaude 3 HaikuGrok 4.7
LMArena Vision9501228
Blueprint-Bench 2—32.5%
Furniture Assembly—20.8%
ScienceQA72%—

Multilingual Grok 4.7 leads

Claude 3 Haiku: 36.0 (#243), Grok 4.7: 50.8 (#116)

BenchmarkClaude 3 HaikuGrok 4.7
LMArena Non-English11781389
LMArena Chinese11551455
LMArena French11951455
LMArena Russian12041397
LMArena Spanish11661400
LMArena German1174—
LMArena Japanese1102—
LMArena Korean1109—

Instruction Following Grok 4.7 leads

Claude 3 Haiku: 61.3 (#247), Grok 4.7: 74.1 (#105)

BenchmarkClaude 3 HaikuGrok 4.7
LMArena Instruction Following11731404

Long Context Grok 4.7 leads

Claude 3 Haiku: 36.1 (#237), Grok 4.7: 43.1 (#104)

BenchmarkClaude 3 HaikuGrok 4.7
LMArena Longer Query11901413

Writing & Preference Grok 4.7 leads

Claude 3 Haiku: 29.7 (#291), Grok 4.7: 70.0 (#24)

BenchmarkClaude 3 HaikuGrok 4.7
LMArena Text11951399
LMArena Creative Writing11571391
EQ-Bench Creative Writing7172007
LMArena Multi-Turn11901393

Frequently asked questions

Is Claude 3 Haiku better than Grok 4.7?

Grok 4.7 is the stronger model overall, scoring 53.1 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or Grok 4.7 better for coding?

Grok 4.7 scores higher on coding benchmarks: 58.0 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Grok 4.7 share?

21 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Grok 4.7 has 39.

Related comparisons

Go deeper