Noometry

Model comparison

Claude Opus 4.8 vs Gemini 3 Flash Preview

Claude Opus 4.8 is the stronger model overall, scoring 60.7 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 4.8's lead doesn't matter for your workload.

Last verified . 48 shared benchmarks.

Claude Opus 4.8 Anthropic

60.7

Rank #13 Confirmed

Gemini 3 Flash Preview Google

52.3

Rank #40 Confirmed

Summary

  • They share 48 benchmarks with published results for both. Claude Opus 4.8 scores higher in 8 categories and Gemini 3 Flash Preview in 2 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Opus 4.8 leads 78.4 to 51.7.
  • The biggest single-benchmark swing is ProofBench: 69% for Claude Opus 4.8 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 4.8.
  • Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 1M.

Side by side

Claude Opus 4.8Gemini 3 Flash Preview
ProviderAnthropicGoogle
Noometry Index60.752.3
Released2026-05-282025-12-17
WeightsProprietaryProprietary
Context window1M1.05M
Max output128K66K
Input $ / M tokens$5$0.50
Output $ / M tokens$25$3
Results tracked6559

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

Category by category

Coding Claude Opus 4.8 leads

Claude Opus 4.8: 59.9 (#12), Gemini 3 Flash Preview: 50.9 (#42)

BenchmarkClaude Opus 4.8Gemini 3 Flash Preview
LMArena WebDev15561439
GSO47.1%9.8%
WeirdML82.9%61.6%
LMArena Coding14901460
ALE-Bench1,5641,367
SWE-bench Verified—75.4%
DeepSWE59%—
FrontierCode46.5%—
SWE-bench Verified (bash only)—75.8%
SWE-bench Multilingual—72.7%
SciCode53.5%—

Agentic & Tool Use Claude Opus 4.8 leads

Claude Opus 4.8: 47.6 (#11), Gemini 3 Flash Preview: 38.7 (#29)

BenchmarkClaude Opus 4.8Gemini 3 Flash Preview
τ²-bench Banking39.7%27.3%
DeepResearch Bench50.2%49.8%
GDP.pdf24%10%
LMArena Search12041198
Vending-Bench 25,7873,635
Terminal-Bench—64.3%
APEX-Agents48.9%—
OSWorld 2.020.6%—
Remote Labor Index8.3%—
τ²-bench Airline—82.5%
τ²-bench Retail—76.8%
τ²-bench Telecom—91.2%
PostTrainBench33.8%—
BALROG—48.1%
GBAEval70.9%—

Reasoning Claude Opus 4.8 leads

Claude Opus 4.8: 64.7 (#16), Gemini 3 Flash Preview: 49.2 (#37)

BenchmarkClaude Opus 4.8Gemini 3 Flash Preview
ARC-AGI-272.1%33.6%
SimpleBench64.8%61.1%
NYT Connections (extended)91.1%83.1%
ARC-AGI-192.5%84.7%
Chess Puzzles34%40%
LMArena Hard Prompts14821465
Mystery Game Puzzles36%26%
DTBench94.9%89.1%
LMCA57.5%43.1%
Epoch Capabilities Index158.21151.8
ForecastBench59.958.5
Kagi LLM Benchmark88.8%—
CritPt20.9%—
EnigmaEval23.5%—
EBR-Bench28.6%—
Surface Evolver Bench87.5%—
Bench to the Future 30.14—

Math Claude Opus 4.8 leads

Claude Opus 4.8: 78.4 (#13), Gemini 3 Flash Preview: 51.7 (#55)

BenchmarkClaude Opus 4.8Gemini 3 Flash Preview
FrontierMath (Tiers 1-3)80%51.2%
FrontierMath Tier 456.1%17.1%
MathArena Final-Answer Competitions91.8%67.6%
OTIS Mock AIME 2024-202598.3%95.6%
ProofBench69%15%
LMArena Math14871473
FrontierMath (Feb 2025 set)47.2%35.6%
FrontierMath Tier 4 (v1)31.3%4.2%

Knowledge Claude Opus 4.8 leads

Claude Opus 4.8: 61.3 (#29), Gemini 3 Flash Preview: 58.8 (#33)

BenchmarkClaude Opus 4.8Gemini 3 Flash Preview
GPQA Diamond91%89.4%
SimpleQA Verified53%66.8%
LMArena Expert15021462
Vectara Hallucination Rate—13.5%

Multimodal Gemini 3 Flash Preview leads

Claude Opus 4.8: 42.9 (#26), Gemini 3 Flash Preview: 45.5 (#16)

BenchmarkClaude Opus 4.8Gemini 3 Flash Preview
LMArena Vision12941285
Blueprint-Bench 214.5%0%
LMArena Document14751413
GeoBench—88%
VPCT—72.6%
Furniture Assembly42.5%—

Multilingual Too close to call

Claude Opus 4.8: 55.2 (#33), Gemini 3 Flash Preview: 55.7 (#27)

BenchmarkClaude Opus 4.8Gemini 3 Flash Preview
LMArena Non-English14501458
LMArena Chinese15071511
LMArena French14811477
LMArena German14721497
LMArena Japanese14401489
LMArena Korean14321443
LMArena Russian14741480
LMArena Spanish14661469

Instruction Following Claude Opus 4.8 leads

Claude Opus 4.8: 77.4 (#24), Gemini 3 Flash Preview: 75.7 (#56)

BenchmarkClaude Opus 4.8Gemini 3 Flash Preview
LMArena Instruction Following14761437

Long Context Claude Opus 4.8 leads

Claude Opus 4.8: 45.4 (#35), Gemini 3 Flash Preview: 44.4 (#67)

BenchmarkClaude Opus 4.8Gemini 3 Flash Preview
LMArena Longer Query14831452

Writing & Preference Claude Opus 4.8 leads

Claude Opus 4.8: 72.0 (#16), Gemini 3 Flash Preview: 65.5 (#45)

BenchmarkClaude Opus 4.8Gemini 3 Flash Preview
LMArena Text14611466
LMArena Creative Writing14541457
LMArena Multi-Turn14761471
EQ-Bench Creative Writing1840—
EQ-Bench 41281—

Frequently asked questions

Is Claude Opus 4.8 better than Gemini 3 Flash Preview?

Claude Opus 4.8 is the stronger model overall, scoring 60.7 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 4.8's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.8 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 4.8 lists at $5 and $25.

Is Claude Opus 4.8 or Gemini 3 Flash Preview better for coding?

Claude Opus 4.8 scores higher on coding benchmarks: 59.9 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 4.8 and Gemini 3 Flash Preview share?

48 benchmarks have published results for both models. Claude Opus 4.8 has 65 scored results on Noometry and Gemini 3 Flash Preview has 59.

Related comparisons

Go deeper