Noometry

Model comparison

Claude Opus 4.7 vs Gemini 3 Flash Preview

Claude Opus 4.7 is the stronger model overall, scoring 58.3 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 4.7's lead doesn't matter for your workload.

Last verified . 50 shared benchmarks.

Claude Opus 4.7 Anthropic

58.3

Rank #19 Confirmed

Gemini 3 Flash Preview Google

52.3

Rank #40 Confirmed

Summary

  • They share 50 benchmarks with published results for both. Claude Opus 4.7 scores higher in 9 categories and Gemini 3 Flash Preview in 1 category; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Opus 4.7 leads 66.7 to 51.7.
  • The biggest single-benchmark swing is NYT Connections (extended): 39% for Claude Opus 4.7 and 83.1% 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 4.7.
  • Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 1M.

Side by side

Claude Opus 4.7Gemini 3 Flash Preview
ProviderAnthropicGoogle
Noometry Index58.352.3
Released2026-04-142025-12-17
WeightsProprietaryProprietary
Context window1M1.05M
Max output128K66K
Input $ / M tokens$5$0.50
Output $ / M tokens$25$3
Results tracked6659

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

Category by category

Coding Claude Opus 4.7 leads

Claude Opus 4.7: 59.6 (#13), Gemini 3 Flash Preview: 50.9 (#42)

BenchmarkClaude Opus 4.7Gemini 3 Flash Preview
SWE-bench Verified83.5%75.4%
LMArena WebDev15581439
GSO44.1%9.8%
WeirdML76.4%61.6%
LMArena Coding15181460
ALE-Bench1,3231,367
FrontierCode38.5%—
SWE-bench Verified (bash only)—75.8%
SWE-bench Multilingual—72.7%
SciCode54.5%—
MirrorCode31.1%—

Agentic & Tool Use Claude Opus 4.7 leads

Claude Opus 4.7: 47.9 (#10), Gemini 3 Flash Preview: 38.7 (#29)

BenchmarkClaude Opus 4.7Gemini 3 Flash Preview
Terminal-Bench80.2%64.3%
τ²-bench Banking40.2%27.3%
GDP.pdf21%10%
LMArena Search12331198
Vending-Bench 210,9373,635
APEX-Agents49.2%—
OSWorld 2.018.2%—
τ²-bench Airline—82.5%
τ²-bench Retail—76.8%
τ²-bench Telecom—91.2%
DeepResearch Bench—49.8%
PostTrainBench28.6%—
BALROG—48.1%
ExploitBench26.5%—
GBAEval43.8%—

Reasoning Claude Opus 4.7 leads

Claude Opus 4.7: 53.8 (#29), Gemini 3 Flash Preview: 49.2 (#37)

BenchmarkClaude Opus 4.7Gemini 3 Flash Preview
ARC-AGI-275.8%33.6%
SimpleBench61.7%61.1%
NYT Connections (extended)39%83.1%
ARC-AGI-193.5%84.7%
Chess Puzzles30%40%
LMArena Hard Prompts15061465
Mystery Game Puzzles28%26%
DTBench94.7%89.1%
LMCA52.2%43.1%
Epoch Capabilities Index156.25151.8
ForecastBench60.358.5
Kagi LLM Benchmark80.7%—
CritPt12%—
Thematic Generalization72.8%—
EBR-Bench19%—

Math Claude Opus 4.7 leads

Claude Opus 4.7: 66.7 (#26), Gemini 3 Flash Preview: 51.7 (#55)

BenchmarkClaude Opus 4.7Gemini 3 Flash Preview
FrontierMath (Tiers 1-3)70.2%51.2%
FrontierMath Tier 431.7%17.1%
MathArena Final-Answer Competitions73.6%67.6%
OTIS Mock AIME 2024-202597.8%95.6%
ProofBench54%15%
LMArena Math14991473
FrontierMath (Feb 2025 set)43.8%35.6%
FrontierMath Tier 4 (v1)22.9%4.2%

Knowledge Claude Opus 4.7 leads

Claude Opus 4.7: 62.6 (#23), Gemini 3 Flash Preview: 58.8 (#33)

BenchmarkClaude Opus 4.7Gemini 3 Flash Preview
GPQA Diamond90.2%89.4%
SimpleQA Verified51.7%66.8%
Vectara Hallucination Rate12%13.5%
LMArena Expert15211462
Humanity's Last Exam36.2%—

Multimodal Gemini 3 Flash Preview leads

Claude Opus 4.7: 41.2 (#38), Gemini 3 Flash Preview: 45.5 (#16)

BenchmarkClaude Opus 4.7Gemini 3 Flash Preview
LMArena Vision13161285
Blueprint-Bench 224.5%0%
LMArena Document14951413
GeoBench—88%
VPCT—72.6%
Furniture Assembly33.3%—

Multilingual Claude Opus 4.7 leads

Claude Opus 4.7: 57.3 (#10), Gemini 3 Flash Preview: 55.7 (#27)

BenchmarkClaude Opus 4.7Gemini 3 Flash Preview
LMArena Non-English14801458
LMArena Chinese15311511
LMArena French15031477
LMArena German14951497
LMArena Japanese14721489
LMArena Korean14641443
LMArena Russian14941480
LMArena Spanish14951469

Instruction Following Claude Opus 4.7 leads

Claude Opus 4.7: 78.4 (#10), Gemini 3 Flash Preview: 75.7 (#56)

BenchmarkClaude Opus 4.7Gemini 3 Flash Preview
LMArena Instruction Following14981437

Long Context Claude Opus 4.7 leads

Claude Opus 4.7: 46.2 (#25), Gemini 3 Flash Preview: 44.4 (#67)

BenchmarkClaude Opus 4.7Gemini 3 Flash Preview
LMArena Longer Query15051452

Writing & Preference Claude Opus 4.7 leads

Claude Opus 4.7: 75.1 (#8), Gemini 3 Flash Preview: 65.5 (#45)

BenchmarkClaude Opus 4.7Gemini 3 Flash Preview
LMArena Text14901466
LMArena Creative Writing14861457
LMArena Multi-Turn15051471
EQ-Bench Creative Writing1914—
EQ-Bench 41311—

Frequently asked questions

Is Claude Opus 4.7 better than Gemini 3 Flash Preview?

Claude Opus 4.7 is the stronger model overall, scoring 58.3 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 4.7's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.7 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 4.7 lists at $5 and $25.

Is Claude Opus 4.7 or Gemini 3 Flash Preview better for coding?

Claude Opus 4.7 scores higher on coding benchmarks: 59.6 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 4.7 and Gemini 3 Flash Preview share?

50 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and Gemini 3 Flash Preview has 59.

Related comparisons

Go deeper