Noometry

Model comparison

Claude 3.5 Haiku vs Gemma 4 31B IT

Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 29.2 on the Noometry Index.

Last verified . 23 shared benchmarks.

Claude 3.5 Haiku Anthropic

29.2

Rank #315 Confirmed

Gemma 4 31B IT Google

43.5

Rank #90 Confirmed

Summary

  • They share 23 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and Gemma 4 31B IT in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemma 4 31B IT leads 43.2 to 14.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.3% for Claude 3.5 Haiku and 73.3% for Gemma 4 31B IT.
  • Gemma 4 31B IT has downloadable open weights; the other is API-only.

Side by side

Claude 3.5 HaikuGemma 4 31B IT
ProviderAnthropicGoogle
Noometry Index29.243.5
Released2024-10-222026-04-02
WeightsProprietaryOpen
Context window—262K
Max output—33K
Input $ / M tokens—$0.09
Output $ / M tokens—$0.34
Results tracked4935

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

Category by category

Coding Gemma 4 31B IT leads

Claude 3.5 Haiku: 32.9 (#265), Gemma 4 31B IT: 42.3 (#108)

BenchmarkClaude 3.5 HaikuGemma 4 31B IT
SciCode27.4%43.4%
WeirdML30.7%52.3%
LMArena Coding12861459
Aider Polyglot28%—
LMArena WebDev—1366
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
BigCodeBench Complete59%—
CadEval32%—
ALE-Bench—925.5

Agentic & Tool Use Not comparable

Claude 3.5 Haiku: 28.0 (#95), Gemma 4 31B IT: —

BenchmarkClaude 3.5 HaikuGemma 4 31B IT
BALROG19.3%—

Reasoning Gemma 4 31B IT leads

Claude 3.5 Haiku: 17.7 (#290), Gemma 4 31B IT: 27.2 (#122)

BenchmarkClaude 3.5 HaikuGemma 4 31B IT
CritPt0%1.4%
LMArena Hard Prompts12511448
DTBench56.7%82.7%
Epoch Capabilities Index127.15142.74
Kagi LLM Benchmark—63.5%
NYT Connections (extended)—70.6%
Chess Puzzles—5%
Thematic Generalization—53%
LiveBench Reasoning28.1%—
LiveBench Data Analysis48.5%—
LMCA—39.3%
Surface Evolver Bench—30.6%
LiveBench43.5%—

Math Gemma 4 31B IT leads

Claude 3.5 Haiku: 14.7 (#300), Gemma 4 31B IT: 43.2 (#81)

BenchmarkClaude 3.5 HaikuGemma 4 31B IT
OTIS Mock AIME 2024-20254.3%73.3%
LMArena Math12441465
Omni-MATH22.4%—
LiveBench Math35.5%—
MATH Level 546.4%—
FrontierMath (Feb 2025 set)0.3%—

Knowledge Gemma 4 31B IT leads

Claude 3.5 Haiku: 18.7 (#281), Gemma 4 31B IT: 37.9 (#151)

BenchmarkClaude 3.5 HaikuGemma 4 31B IT
GPQA Diamond38.1%75.8%
LMArena Expert12081465
SimpleQA Verified—10.4%
MMLU-Pro60.5%—
Confabulations36.7%—
Vectara Hallucination Rate—7.4%
GPQA (HELM)36.3%—
MMLU74.3%—

Multimodal Gemma 4 31B IT leads

Claude 3.5 Haiku: 26.8 (#117), Gemma 4 31B IT: 41.6 (#34)

BenchmarkClaude 3.5 HaikuGemma 4 31B IT
LMArena Vision10921277
GeoBench34%—
LMArena Document—1425

Multilingual Gemma 4 31B IT leads

Claude 3.5 Haiku: 40.0 (#218), Gemma 4 31B IT: 53.8 (#57)

BenchmarkClaude 3.5 HaikuGemma 4 31B IT
LMArena Non-English12381431
LMArena Chinese12291476
LMArena French12641435
LMArena Russian12531460
LMArena Spanish12611444
LMArena German1237—
LMArena Japanese1175—
LMArena Korean1173—

Instruction Following Gemma 4 31B IT leads

Claude 3.5 Haiku: 62.9 (#234), Gemma 4 31B IT: 75.5 (#61)

BenchmarkClaude 3.5 HaikuGemma 4 31B IT
LMArena Instruction Following12411433
LiveBench Instruction Following61.9%—
IFEval79.2%—

Long Context Gemma 4 31B IT leads

Claude 3.5 Haiku: 38.3 (#200), Gemma 4 31B IT: 44.2 (#71)

BenchmarkClaude 3.5 HaikuGemma 4 31B IT
LMArena Longer Query12611446

Writing & Preference Gemma 4 31B IT leads

Claude 3.5 Haiku: 42.7 (#234), Gemma 4 31B IT: 60.5 (#96)

BenchmarkClaude 3.5 HaikuGemma 4 31B IT
LMArena Text12551443
LMArena Creative Writing12331415
EQ-Bench Creative Writing11461368
LMArena Multi-Turn12651452
Short-Story Creative Writing73.5%—
WildBench76%—
EQ-Bench 4—1120
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than Gemma 4 31B IT?

Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 29.2 on the Noometry Index.

Is Claude 3.5 Haiku or Gemma 4 31B IT better for coding?

Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and Gemma 4 31B IT share?

23 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Gemma 4 31B IT has 35.

Related comparisons

Go deeper