Noometry

Model comparison

Claude Sonnet 4.5 vs Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 44.0 on the Noometry Index.

Last verified . 55 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.0

Rank #76 Confirmed

Gemini 3.1 Pro Preview Google

56.7

Rank #20 Confirmed

Summary

  • They share 55 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 3 categories and Gemini 3.1 Pro Preview in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 26.9.
  • The biggest single-benchmark swing is ARC-AGI-2: 13.6% for Claude Sonnet 4.5 and 77.1% for Gemini 3.1 Pro Preview.
  • Gemini 3.1 Pro Preview is cheaper at $2 / $12 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
  • Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 1M.

Side by side

Claude Sonnet 4.5Gemini 3.1 Pro Preview
ProviderAnthropicGoogle
Noometry Index44.056.7
Released2025-09-292026-02-19
WeightsProprietaryProprietary
Context window1M1.05M
Max output64K66K
Input $ / M tokens$3$2
Output $ / M tokens$15$12
Results tracked7371

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

Category by category

Coding Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 47.8 (#54), Gemini 3.1 Pro Preview: 42.7 (#88)

BenchmarkClaude Sonnet 4.5Gemini 3.1 Pro Preview
SWE-bench Verified71.3%75.6%
LMArena WebDev13931446
SciCode44.7%58.9%
GSO14.7%22.6%
WeirdML47.7%72.1%
LMArena Coding14891483
ALE-Bench796.151,161
AlgoTune1.522.02
DeepSWE—11.7%
SWE-bench Verified (bash only)71.4%—
SWE-bench Multilingual67%—
MirrorCode—8.9%

Agentic & Tool Use Too close to call

Claude Sonnet 4.5: 38.1 (#30), Gemini 3.1 Pro Preview: 37.7 (#33)

BenchmarkClaude Sonnet 4.5Gemini 3.1 Pro Preview
Terminal-Bench46.5%80.2%
τ²-bench Banking25.3%26%
DeepResearch Bench52.6%47.8%
LMArena Search11591211
METR Time Horizons67.4%77%
Vending-Bench 23,8393,774
APEX-Agents—35.3%
Berkeley Function Calling Leaderboard73.2%—
GDPval42.5%—
Remote Labor Index2.1%—
τ²-bench Airline72%—
τ²-bench Retail72.4%—
τ²-bench Telecom84.9%—
Cybench60%—
OSWorld62.9%—
PostTrainBench—22%
BALROG—57%
ExploitBench—26.1%
GBAEval—0.8%
GDP.pdf—17%

Reasoning Gemini 3.1 Pro Preview leads

Claude Sonnet 4.5: 26.9 (#113), Gemini 3.1 Pro Preview: 71.7 (#9)

BenchmarkClaude Sonnet 4.5Gemini 3.1 Pro Preview
ARC-AGI-213.6%77.1%
SimpleBench54.3%79.6%
NYT Connections (extended)37.3%97.4%
ARC-AGI-163.7%98%
CritPt1.1%17.7%
Chess Puzzles12%55%
EnigmaEval6%36.8%
EBR-Bench2.4%14.3%
LMArena Hard Prompts14621484
Mystery Game Puzzles17%34%
DTBench83.2%97.1%
LMCA38.8%53.8%
Epoch Capabilities Index146.84154.92
ForecastBench61.959
Kagi LLM Benchmark57.9%—
Thematic Generalization—79.4%

Math Gemini 3.1 Pro Preview leads

Claude Sonnet 4.5: 31.9 (#190), Gemini 3.1 Pro Preview: 61.8 (#28)

BenchmarkClaude Sonnet 4.5Gemini 3.1 Pro Preview
FrontierMath (Tiers 1-3)23.9%59.6%
FrontierMath Tier 42.4%26.8%
OTIS Mock AIME 2024-202577.8%95.6%
ProofBench19%26%
LMArena Math14481485
FrontierMath (Feb 2025 set)15.2%36.9%
FrontierMath Tier 4 (v1)4.2%16.7%
MathArena Final-Answer Competitions—86.5%
Omni-MATH55.3%—
MATH Level 597.7%—

Knowledge Gemini 3.1 Pro Preview leads

Claude Sonnet 4.5: 48.4 (#70), Gemini 3.1 Pro Preview: 71.8 (#3)

BenchmarkClaude Sonnet 4.5Gemini 3.1 Pro Preview
GPQA Diamond82.3%94.4%
Humanity's Last Exam13.7%46.4%
SimpleQA Verified30.7%73.5%
Vectara Hallucination Rate12%10.4%
LMArena Expert14831484
MMLU-Pro86.9%—
GPQA (HELM)68.6%—

Multimodal Gemini 3.1 Pro Preview leads

Claude Sonnet 4.5: 34.1 (#84), Gemini 3.1 Pro Preview: 38.1 (#60)

BenchmarkClaude Sonnet 4.5Gemini 3.1 Pro Preview
LMArena Document14501444
LMArena Vision—1296
VPCT39.8%—
Blueprint-Bench 2—26.5%
Furniture Assembly—26.7%

Multilingual Gemini 3.1 Pro Preview leads

Claude Sonnet 4.5: 53.6 (#65), Gemini 3.1 Pro Preview: 57.1 (#11)

BenchmarkClaude Sonnet 4.5Gemini 3.1 Pro Preview
LMArena Non-English14251475
LMArena Chinese14591528
LMArena French14591488
LMArena German14271491
LMArena Japanese13901494
LMArena Korean14031458
LMArena Russian14361496
LMArena Spanish14571480

Instruction Following Gemini 3.1 Pro Preview leads

Claude Sonnet 4.5: 75.2 (#74), Gemini 3.1 Pro Preview: 77.1 (#31)

BenchmarkClaude Sonnet 4.5Gemini 3.1 Pro Preview
LMArena Instruction Following14591465
IFEval85%—

Long Context Gemini 3.1 Pro Preview leads

Claude Sonnet 4.5: 45.2 (#45), Gemini 3.1 Pro Preview: 47.3 (#17)

BenchmarkClaude Sonnet 4.5Gemini 3.1 Pro Preview
LMArena Longer Query14761482
CL-bench—20.8%
CL-bench Life—16.9%

Writing & Preference Too close to call

Claude Sonnet 4.5: 66.7 (#33), Gemini 3.1 Pro Preview: 66.3 (#36)

BenchmarkClaude Sonnet 4.5Gemini 3.1 Pro Preview
LMArena Text14391480
LMArena Creative Writing14421482
EQ-Bench Creative Writing16781491
LMArena Multi-Turn14651486
WildBench85.4%—
EQ-Bench 4—1142

Frequently asked questions

Is Claude Sonnet 4.5 better than Gemini 3.1 Pro Preview?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 44.0 on the Noometry Index.

Which is cheaper, Claude Sonnet 4.5 or Gemini 3.1 Pro Preview?

Gemini 3.1 Pro Preview is cheaper. It lists at $2 per million input tokens and $12 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

Is Claude Sonnet 4.5 or Gemini 3.1 Pro Preview better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.8 versus 42.7 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 1M.

How many benchmarks do Claude Sonnet 4.5 and Gemini 3.1 Pro Preview share?

55 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Gemini 3.1 Pro Preview has 71.

Related comparisons

Go deeper