Noometry

Model comparison

Claude Opus 4.5 vs Gemini 3 Flash Preview

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 50.5 on the Noometry Index.

Last verified . 55 shared benchmarks.

Claude Opus 4.5 Anthropic

50.5

Rank #47 Confirmed

Gemini 3 Flash Preview Google

52.3

Rank #40 Confirmed

Summary

  • They share 55 benchmarks with published results for both. Claude Opus 4.5 scores higher in 5 categories and Gemini 3 Flash Preview in 5 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in multimodal, where Gemini 3 Flash Preview leads 45.5 to 31.4.
  • The biggest single-benchmark swing is VPCT: 40% for Claude Opus 4.5 and 72.6% for Gemini 3 Flash Preview.
  • Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
  • Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 200K.

Side by side

Claude Opus 4.5Gemini 3 Flash Preview
ProviderAnthropicGoogle
Noometry Index50.552.3
Released2025-11-012025-12-17
WeightsProprietaryProprietary
Context window200K1.05M
Max output64K66K
Input $ / M tokens$5$0.50
Output $ / M tokens$25$3
Results tracked6959

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: 54.8 (#27), Gemini 3 Flash Preview: 50.9 (#42)

BenchmarkClaude Opus 4.5Gemini 3 Flash Preview
SWE-bench Verified76.7%75.4%
SWE-bench Verified (bash only)76.8%75.8%
LMArena WebDev14941439
SWE-bench Multilingual70.7%72.7%
GSO26.5%9.8%
WeirdML63.7%61.6%
LMArena Coding15041460
ALE-Bench1,0251,367
AlgoTune1.77—

Agentic & Tool Use Claude Opus 4.5 leads

Claude Opus 4.5: 47.3 (#12), Gemini 3 Flash Preview: 38.7 (#29)

BenchmarkClaude Opus 4.5Gemini 3 Flash Preview
Terminal-Bench63.1%64.3%
τ²-bench Airline84%82.5%
τ²-bench Banking24.7%27.3%
τ²-bench Retail79.6%76.8%
τ²-bench Telecom92.3%91.2%
DeepResearch Bench54.8%49.8%
BALROG43.5%48.1%
LMArena Search11801198
Vending-Bench 24,9673,635
Berkeley Function Calling Leaderboard77.5%—
GDPval45.5%—
Remote Labor Index3.8%—
Cybench82%—
OSWorld66.3%—
GDP.pdf—10%
METR Time Horizons75%—

Reasoning Gemini 3 Flash Preview leads

Claude Opus 4.5: 42.6 (#51), Gemini 3 Flash Preview: 49.2 (#37)

BenchmarkClaude Opus 4.5Gemini 3 Flash Preview
ARC-AGI-237.6%33.6%
SimpleBench62%61.1%
NYT Connections (extended)52.5%83.1%
ARC-AGI-180%84.7%
Chess Puzzles12%40%
LMArena Hard Prompts14761465
Mystery Game Puzzles22%26%
DTBench89.9%89.1%
LMCA44.5%43.1%
Epoch Capabilities Index150.09151.8
ForecastBench60.758.5
Kagi LLM Benchmark80.2%—
EnigmaEval11.9%—
EBR-Bench14.3%—

Math Gemini 3 Flash Preview leads

Claude Opus 4.5: 38.6 (#132), Gemini 3 Flash Preview: 51.7 (#55)

BenchmarkClaude Opus 4.5Gemini 3 Flash Preview
FrontierMath (Tiers 1-3)34.4%51.2%
FrontierMath Tier 44.9%17.1%
OTIS Mock AIME 2024-202586.1%95.6%
ProofBench36%15%
LMArena Math14631473
FrontierMath (Feb 2025 set)20.7%35.6%
FrontierMath Tier 4 (v1)4.2%4.2%
MathArena Final-Answer Competitions—67.6%

Knowledge Gemini 3 Flash Preview leads

Claude Opus 4.5: 56.5 (#44), Gemini 3 Flash Preview: 58.8 (#33)

BenchmarkClaude Opus 4.5Gemini 3 Flash Preview
GPQA Diamond86%89.4%
SimpleQA Verified45.7%66.8%
Vectara Hallucination Rate10.9%13.5%
LMArena Expert14871462
Humanity's Last Exam25.2%—

Multimodal Gemini 3 Flash Preview leads

Claude Opus 4.5: 31.4 (#107), Gemini 3 Flash Preview: 45.5 (#16)

BenchmarkClaude Opus 4.5Gemini 3 Flash Preview
GeoBench75%88%
VPCT40%72.6%
LMArena Document14621413
LMArena Vision—1285
Blueprint-Bench 2—0%
Furniture Assembly28.3%—

Multilingual Gemini 3 Flash Preview leads

Claude Opus 4.5: 54.3 (#47), Gemini 3 Flash Preview: 55.7 (#27)

BenchmarkClaude Opus 4.5Gemini 3 Flash Preview
LMArena Non-English14381458
LMArena Chinese14701511
LMArena French14711477
LMArena German14491497
LMArena Japanese14161489
LMArena Korean14241443
LMArena Russian14471480
LMArena Spanish14581469

Instruction Following Claude Opus 4.5 leads

Claude Opus 4.5: 77.5 (#19), Gemini 3 Flash Preview: 75.7 (#56)

BenchmarkClaude Opus 4.5Gemini 3 Flash Preview
LMArena Instruction Following14781437

Long Context Claude Opus 4.5 leads

Claude Opus 4.5: 46.5 (#22), Gemini 3 Flash Preview: 44.4 (#67)

BenchmarkClaude Opus 4.5Gemini 3 Flash Preview
LMArena Longer Query14801452
CL-bench21.1%—

Writing & Preference Claude Opus 4.5 leads

Claude Opus 4.5: 68.1 (#28), Gemini 3 Flash Preview: 65.5 (#45)

BenchmarkClaude Opus 4.5Gemini 3 Flash Preview
LMArena Text14511466
LMArena Creative Writing14451457
LMArena Multi-Turn14661471
EQ-Bench Creative Writing1687—

Frequently asked questions

Is Claude Opus 4.5 better than Gemini 3 Flash Preview?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 50.5 on the Noometry Index.

Which is cheaper, Claude Opus 4.5 or Gemini 3 Flash Preview?

Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; Claude Opus 4.5 lists at $5 and $25.

Is Claude Opus 4.5 or Gemini 3 Flash Preview better for coding?

Claude Opus 4.5 scores higher on coding benchmarks: 54.8 versus 50.9 in the Noometry coding category.

Which has the bigger context window?

Gemini 3 Flash Preview does, with 1.05M tokens against 200K.

How many benchmarks do Claude Opus 4.5 and Gemini 3 Flash Preview share?

55 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and Gemini 3 Flash Preview has 59.

Related comparisons

Go deeper