Noometry

Model comparison

Claude Opus 5 vs Gemini 3 Flash Preview

Claude Opus 5 is the stronger model overall, scoring 67.8 to 52.3 on the Noometry Index. Gemini 3 Flash Preview costs 8.9× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.

Last verified . 42 shared benchmarks.

Claude Opus 5 Anthropic

67.8

Rank #4 Confirmed

Gemini 3 Flash Preview Google

52.3

Rank #40 Confirmed

Summary

  • They share 42 benchmarks with published results for both. Claude Opus 5 scores higher in 10 categories and Gemini 3 Flash Preview in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Opus 5 leads 86.2 to 51.7.
  • The biggest single-benchmark swing is ProofBench: 99% for Claude Opus 5 and 15% 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 5.
  • Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 1M.

Side by side

Claude Opus 5Gemini 3 Flash Preview
ProviderAnthropicGoogle
Noometry Index67.852.3
Released2026-07-242025-12-17
WeightsProprietaryProprietary
Context window1M1.05M
Max output128K66K
Input $ / M tokens$5$0.50
Output $ / M tokens$25$3
Results tracked5759

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

Category by category

Coding Claude Opus 5 leads

Claude Opus 5: 67.5 (#5), Gemini 3 Flash Preview: 50.9 (#42)

BenchmarkClaude Opus 5Gemini 3 Flash Preview
LMArena WebDev16911439
WeirdML91.8%61.6%
LMArena Coding15341460
ALE-Bench2,1651,367
SWE-bench Verified—75.4%
DeepSWE73.6%—
FrontierCode53.4%—
SWE-bench Verified (bash only)—75.8%
CursorBench46.6%—
SWE-bench Multilingual—72.7%
FrontierSWE52%—
SciCode56.4%—
GSO—9.8%

Agentic & Tool Use Claude Opus 5 leads

Claude Opus 5: 55.6 (#1), Gemini 3 Flash Preview: 38.7 (#29)

BenchmarkClaude Opus 5Gemini 3 Flash Preview
τ²-bench Banking48.7%27.3%
BALROG63.4%48.1%
GDP.pdf24%10%
Vending-Bench 211,1823,635
Terminal-Bench—64.3%
APEX-Agents65.8%—
OSWorld 2.031.4%—
τ²-bench Airline—82.5%
τ²-bench Retail—76.8%
τ²-bench Telecom—91.2%
DeepResearch Bench—49.8%
PostTrainBench35%—
GBAEval79.6%—
LMArena Search—1198

Reasoning Claude Opus 5 leads

Claude Opus 5: 77.2 (#4), Gemini 3 Flash Preview: 49.2 (#37)

BenchmarkClaude Opus 5Gemini 3 Flash Preview
ARC-AGI-290.4%33.6%
SimpleBench80.6%61.1%
NYT Connections (extended)94.3%83.1%
ARC-AGI-197.5%84.7%
Chess Puzzles42%40%
LMArena Hard Prompts15261465
Mystery Game Puzzles59%26%
DTBench97.9%89.1%
LMCA64.5%43.1%
Epoch Capabilities Index162.78151.8
CritPt29.1%—
EBR-Bench45.7%—
Bench to the Future 30.12—
ForecastBench—58.5

Math Claude Opus 5 leads

Claude Opus 5: 86.2 (#8), Gemini 3 Flash Preview: 51.7 (#55)

BenchmarkClaude Opus 5Gemini 3 Flash Preview
FrontierMath (Tiers 1-3)85.6%51.2%
FrontierMath Tier 473.2%17.1%
OTIS Mock AIME 2024-202598.9%95.6%
ProofBench99%15%
LMArena Math15311473
MathArena Final-Answer Competitions—67.6%
FrontierMath (Feb 2025 set)—35.6%
FrontierMath Tier 4 (v1)—4.2%

Knowledge Claude Opus 5 leads

Claude Opus 5: 66.8 (#9), Gemini 3 Flash Preview: 58.8 (#33)

BenchmarkClaude Opus 5Gemini 3 Flash Preview
GPQA Diamond93.9%89.4%
SimpleQA Verified59.9%66.8%
LMArena Expert15571462
Vectara Hallucination Rate—13.5%

Multimodal Claude Opus 5 leads

Claude Opus 5: 50.8 (#8), Gemini 3 Flash Preview: 45.5 (#16)

BenchmarkClaude Opus 5Gemini 3 Flash Preview
LMArena Vision13191285
Blueprint-Bench 230.4%0%
LMArena Document15161413
GeoBench—88%
VPCT—72.6%
Furniture Assembly60.8%—

Multilingual Claude Opus 5 leads

Claude Opus 5: 58.8 (#4), Gemini 3 Flash Preview: 55.7 (#27)

BenchmarkClaude Opus 5Gemini 3 Flash Preview
LMArena Non-English15011458
LMArena Chinese15741511
LMArena French15191477
LMArena German15241497
LMArena Japanese15161489
LMArena Korean15211443
LMArena Russian15071480
LMArena Spanish15191469

Instruction Following Claude Opus 5 leads

Claude Opus 5: 79.2 (#7), Gemini 3 Flash Preview: 75.7 (#56)

BenchmarkClaude Opus 5Gemini 3 Flash Preview
LMArena Instruction Following15171437

Long Context Claude Opus 5 leads

Claude Opus 5: 46.5 (#21), Gemini 3 Flash Preview: 44.4 (#67)

BenchmarkClaude Opus 5Gemini 3 Flash Preview
LMArena Longer Query15151452

Writing & Preference Claude Opus 5 leads

Claude Opus 5: 79.2 (#1), Gemini 3 Flash Preview: 65.5 (#45)

BenchmarkClaude Opus 5Gemini 3 Flash Preview
LMArena Text15071466
LMArena Creative Writing14911457
LMArena Multi-Turn14991471
EQ-Bench Creative Writing2133—
EQ-Bench 41385—

Frequently asked questions

Is Claude Opus 5 better than Gemini 3 Flash Preview?

Claude Opus 5 is the stronger model overall, scoring 67.8 to 52.3 on the Noometry Index. Gemini 3 Flash Preview costs 8.9× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 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 5 lists at $5 and $25.

Is Claude Opus 5 or Gemini 3 Flash Preview better for coding?

Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 50.9 in the Noometry coding category.

Which has the bigger context window?

Gemini 3 Flash Preview does, with 1.05M tokens against 1M.

How many benchmarks do Claude Opus 5 and Gemini 3 Flash Preview share?

42 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and Gemini 3 Flash Preview has 59.

Related comparisons

Go deeper