Noometry

Model comparison

Claude Opus 4.5 vs Gemma 4 31B IT

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 43.2 on the Noometry Index. Gemma 4 31B IT costs 66× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Last verified . 29 shared benchmarks.

Claude Opus 4.5 Anthropic

50.5

Rank #39 Confirmed

Gemma 4 31B IT Google

43.2

Rank #85 Confirmed

Summary

  • They share 29 benchmarks with published results for both. Claude Opus 4.5 scores higher in 7 categories and Gemma 4 31B IT in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Claude Opus 4.5 leads 56.4 to 37.9.
  • The biggest single-benchmark swing is SimpleQA Verified: 45.7% for Claude Opus 4.5 and 10.4% for Gemma 4 31B IT.
  • Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
  • Gemma 4 31B IT accepts more context: 262K tokens versus 200K.
  • Gemma 4 31B IT has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.5Gemma 4 31B IT
ProviderAnthropicGoogle
Noometry Index50.543.2
Released2025-11-012026-04-02
WeightsProprietaryOpen
Context window200K262K
Max output64K33K
Input $ / M tokens$5$0.09
Output $ / M tokens$25$0.34
Results tracked6935

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

Category by category

Coding Claude Opus 4.5 leads

Claude Opus 4.5: 55.4 (#21), Gemma 4 31B IT: 41.9 (#98)

BenchmarkClaude Opus 4.5Gemma 4 31B IT
LMArena WebDev14931364
WeirdML63.7%52.3%
LMArena Coding15041459
ALE-Bench1,025925.5
SWE-bench Verified76.7%—
SWE-bench Verified (bash only)76.8%—
SWE-bench Multilingual70.7%—
SciCode—43.4%
GSO26.5%—
AlgoTune1.77—

Agentic & Tool Use Not comparable

Claude Opus 4.5: 47.2 (#11), Gemma 4 31B IT: —

BenchmarkClaude Opus 4.5Gemma 4 31B IT
Terminal-Bench63.1%—
Berkeley Function Calling Leaderboard77.5%—
GDPval45.5%—
Remote Labor Index3.8%—
τ²-bench Airline84%—
τ²-bench Banking24.7%—
τ²-bench Retail79.6%—
τ²-bench Telecom92.3%—
Cybench82%—
DeepResearch Bench54.8%—
OSWorld66.3%—
BALROG43.5%—
LMArena Search1180—
METR Time Horizons75%—
Vending-Bench 24,967—

Reasoning Claude Opus 4.5 leads

Claude Opus 4.5: 42.5 (#43), Gemma 4 31B IT: 26.4 (#119)

BenchmarkClaude Opus 4.5Gemma 4 31B IT
Kagi LLM Benchmark80.2%63.5%
NYT Connections (extended)52.5%70.6%
Chess Puzzles12%5%
LMArena Hard Prompts14761448
DTBench89.9%82.7%
LMCA44.5%39.3%
Epoch Capabilities Index150.1142.74
ARC-AGI-237.6%—
SimpleBench62%—
ARC-AGI-180%—
CritPt—1.4%
EnigmaEval11.9%—
Thematic Generalization—53%
EBR-Bench14.3%—
Mystery Game Puzzles22%—
Surface Evolver Bench—30.6%
ForecastBench60.7—

Math Gemma 4 31B IT leads

Claude Opus 4.5: 38.5 (#85), Gemma 4 31B IT: 41.3 (#72)

BenchmarkClaude Opus 4.5Gemma 4 31B IT
OTIS Mock AIME 2024-202586.1%73.3%
LMArena Math14631464
FrontierMath (Tiers 1-3)34.4%—
FrontierMath Tier 44.9%—
ProofBench36%—
FrontierMath (Feb 2025 set)20.7%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Claude Opus 4.5 leads

Claude Opus 4.5: 56.4 (#38), Gemma 4 31B IT: 37.9 (#141)

BenchmarkClaude Opus 4.5Gemma 4 31B IT
GPQA Diamond86%75.8%
SimpleQA Verified45.7%10.4%
Vectara Hallucination Rate10.9%7.4%
LMArena Expert14881465
Humanity's Last Exam25.2%—

Multimodal Gemma 4 31B IT leads

Claude Opus 4.5: 31.1 (#99), Gemma 4 31B IT: 41.0 (#32)

BenchmarkClaude Opus 4.5Gemma 4 31B IT
LMArena Document14621425
LMArena Vision—1278
GeoBench75%—
VPCT40%—
Furniture Assembly28.3%—

Multilingual Too close to call

Claude Opus 4.5: 54.5 (#45), Gemma 4 31B IT: 54.0 (#52)

BenchmarkClaude Opus 4.5Gemma 4 31B IT
LMArena Non-English14381431
LMArena Chinese14701478
LMArena French14711436
LMArena Russian14481462
LMArena Spanish14551443
LMArena German1449—
LMArena Japanese1415—
LMArena Korean1424—

Instruction Following Claude Opus 4.5 leads

Claude Opus 4.5: 77.7 (#20), Gemma 4 31B IT: 75.6 (#58)

BenchmarkClaude Opus 4.5Gemma 4 31B IT
LMArena Instruction Following14781433

Long Context Claude Opus 4.5 leads

Claude Opus 4.5: 46.4 (#21), Gemma 4 31B IT: 44.2 (#67)

BenchmarkClaude Opus 4.5Gemma 4 31B IT
LMArena Longer Query14801446
CL-bench21.1%—

Writing & Preference Claude Opus 4.5 leads

Claude Opus 4.5: 68.2 (#28), Gemma 4 31B IT: 60.7 (#92)

BenchmarkClaude Opus 4.5Gemma 4 31B IT
LMArena Text14511443
LMArena Creative Writing14451416
EQ-Bench Creative Writing16871368
LMArena Multi-Turn14661452
EQ-Bench 4—1120

Frequently asked questions

Is Claude Opus 4.5 better than Gemma 4 31B IT?

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 43.2 on the Noometry Index. Gemma 4 31B IT costs 66× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.5 or Gemma 4 31B IT?

Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Claude Opus 4.5 lists at $5 and $25.

Is Claude Opus 4.5 or Gemma 4 31B IT better for coding?

Claude Opus 4.5 scores higher on coding benchmarks: 55.4 versus 41.9 in the Noometry coding category.

Which has the bigger context window?

Gemma 4 31B IT does, with 262K tokens against 200K.

How many benchmarks do Claude Opus 4.5 and Gemma 4 31B IT share?

29 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and Gemma 4 31B IT has 35.

Related comparisons

Go deeper