Noometry

Model comparison

Claude Sonnet 4.5 vs Gemini 3.8 Flash

Gemini 3.8 Flash is the stronger model overall, scoring 59.5 to 44.0 on the Noometry Index.

Last verified . 36 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.0

Rank #76 Confirmed

Gemini 3.8 Flash Google

59.5

Rank #13 Confirmed

Summary

  • They share 36 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 0 categories and Gemini 3.8 Flash in 10 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.8 Flash leads 64.7 to 26.9.
  • The biggest single-benchmark swing is NYT Connections (extended): 37.3% for Claude Sonnet 4.5 and 97.4% for Gemini 3.8 Flash.
  • Gemini 3.8 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
  • Gemini 3.8 Flash accepts more context: 1.05M tokens versus 1M.

Side by side

Claude Sonnet 4.5Gemini 3.8 Flash
ProviderAnthropicGoogle
Noometry Index44.059.5
Released2025-09-292026-09-02
WeightsProprietaryProprietary
Context window1M1.05M
Max output64K66K
Input $ / M tokens$3$0.75
Output $ / M tokens$15$3.75
Results tracked7346

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

Category by category

Coding Gemini 3.8 Flash leads

Claude Sonnet 4.5: 47.8 (#54), Gemini 3.8 Flash: 56.4 (#17)

BenchmarkClaude Sonnet 4.5Gemini 3.8 Flash
LMArena WebDev13931581
SciCode44.7%56.6%
LMArena Coding14891512
ALE-Bench796.151,270
SWE-bench Verified71.3%—
DeepSWE—73.8%
FrontierCode—41.2%
SWE-bench Verified (bash only)71.4%—
CursorBench—39.6%
SWE-bench Multilingual67%—
FrontierSWE—19.6%
GSO14.7%—
WeirdML47.7%—
AlgoTune1.52—

Agentic & Tool Use Gemini 3.8 Flash leads

Claude Sonnet 4.5: 38.1 (#30), Gemini 3.8 Flash: 40.3 (#22)

BenchmarkClaude Sonnet 4.5Gemini 3.8 Flash
Vending-Bench 23,8395,094
Terminal-Bench46.5%—
APEX-Agents—64.3%
Berkeley Function Calling Leaderboard73.2%—
GDPval42.5%—
Remote Labor Index2.1%—
τ²-bench Airline72%—
τ²-bench Banking25.3%—
τ²-bench Retail72.4%—
τ²-bench Telecom84.9%—
Cybench60%—
DeepResearch Bench52.6%—
OSWorld62.9%—
GDP.pdf—23.4%
LMArena Search1159—
METR Time Horizons67.4%—

Reasoning Gemini 3.8 Flash leads

Claude Sonnet 4.5: 26.9 (#113), Gemini 3.8 Flash: 64.7 (#13)

BenchmarkClaude Sonnet 4.5Gemini 3.8 Flash
NYT Connections (extended)37.3%97.4%
CritPt1.1%18.3%
Chess Puzzles12%61%
LMArena Hard Prompts14621506
Mystery Game Puzzles17%47%
DTBench83.2%95.7%
LMCA38.8%52.9%
Epoch Capabilities Index146.84157.13
ARC-AGI-213.6%—
SimpleBench54.3%—
Kagi LLM Benchmark57.9%—
ARC-AGI-163.7%—
EnigmaEval6%—
EBR-Bench2.4%—
Surface Evolver Bench—76.9%
ForecastBench61.9—

Math Gemini 3.8 Flash leads

Claude Sonnet 4.5: 31.9 (#190), Gemini 3.8 Flash: 65.2 (#22)

BenchmarkClaude Sonnet 4.5Gemini 3.8 Flash
FrontierMath (Tiers 1-3)23.9%68.4%
FrontierMath Tier 42.4%22%
OTIS Mock AIME 2024-202577.8%98.9%
ProofBench19%48%
LMArena Math14481528
Omni-MATH55.3%—
MATH Level 597.7%—
FrontierMath (Feb 2025 set)15.2%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Gemini 3.8 Flash leads

Claude Sonnet 4.5: 48.4 (#70), Gemini 3.8 Flash: 74.9 (#2)

BenchmarkClaude Sonnet 4.5Gemini 3.8 Flash
GPQA Diamond82.3%95.4%
Humanity's Last Exam13.7%44.5%
SimpleQA Verified30.7%69.7%
LMArena Expert14831529
MMLU-Pro86.9%—
Vectara Hallucination Rate12%—
GPQA (HELM)68.6%—

Multimodal Gemini 3.8 Flash leads

Claude Sonnet 4.5: 34.1 (#84), Gemini 3.8 Flash: 40.9 (#33)

BenchmarkClaude Sonnet 4.5Gemini 3.8 Flash
LMArena Vision—1312
VPCT39.8%—
Blueprint-Bench 2—38.6%
Furniture Assembly—31.7%
LMArena Document1450—

Multilingual Gemini 3.8 Flash leads

Claude Sonnet 4.5: 53.6 (#65), Gemini 3.8 Flash: 57.9 (#5)

BenchmarkClaude Sonnet 4.5Gemini 3.8 Flash
LMArena Non-English14251486
LMArena Chinese14591547
LMArena French14591502
LMArena German14271470
LMArena Japanese13901505
LMArena Korean14031479
LMArena Russian14361507
LMArena Spanish14571492

Instruction Following Gemini 3.8 Flash leads

Claude Sonnet 4.5: 75.2 (#74), Gemini 3.8 Flash: 78.2 (#11)

BenchmarkClaude Sonnet 4.5Gemini 3.8 Flash
LMArena Instruction Following14591489
IFEval85%—

Long Context Too close to call

Claude Sonnet 4.5: 45.2 (#45), Gemini 3.8 Flash: 46.2 (#23)

BenchmarkClaude Sonnet 4.5Gemini 3.8 Flash
LMArena Longer Query14761506

Writing & Preference Gemini 3.8 Flash leads

Claude Sonnet 4.5: 66.7 (#33), Gemini 3.8 Flash: 72.1 (#16)

BenchmarkClaude Sonnet 4.5Gemini 3.8 Flash
LMArena Text14391494
LMArena Creative Writing14421485
EQ-Bench Creative Writing16781748
LMArena Multi-Turn14651503
WildBench85.4%—

Frequently asked questions

Is Claude Sonnet 4.5 better than Gemini 3.8 Flash?

Gemini 3.8 Flash is the stronger model overall, scoring 59.5 to 44.0 on the Noometry Index.

Which is cheaper, Claude Sonnet 4.5 or Gemini 3.8 Flash?

Gemini 3.8 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

Is Claude Sonnet 4.5 or Gemini 3.8 Flash better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 56.4 versus 47.8 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.8 Flash does, with 1.05M tokens against 1M.

How many benchmarks do Claude Sonnet 4.5 and Gemini 3.8 Flash share?

36 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Gemini 3.8 Flash has 46.

Related comparisons

Go deeper