Noometry

Model comparison

Claude Sonnet 5 vs Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 54.6 on the Noometry Index.

Last verified . 47 shared benchmarks.

Claude Sonnet 5 Anthropic

54.6

Rank #29 Confirmed

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

Summary

  • They share 47 benchmarks with published results for both. Claude Sonnet 5 scores higher in 5 categories and Gemini 3.1 Pro Preview in 5 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 49.1.
  • The biggest single-benchmark swing is GBAEval: 65.3% for Claude Sonnet 5 and 0.8% for Gemini 3.1 Pro Preview.
  • Claude Sonnet 5 is cheaper at $2 / $10 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
  • Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 1M.

Side by side

Claude Sonnet 5Gemini 3.1 Pro Preview
ProviderAnthropicGoogle
Noometry Index54.656.7
Released2026-06-292026-02-19
WeightsProprietaryProprietary
Context window1M1.05M
Max output128K66K
Input $ / M tokens$2$2
Output $ / M tokens$10$12
Results tracked5171

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

Category by category

Coding Claude Sonnet 5 leads

Claude Sonnet 5: 55.5 (#26), Gemini 3.1 Pro Preview: 42.5 (#99)

BenchmarkClaude Sonnet 5Gemini 3.1 Pro Preview
DeepSWE53.8%11.7%
LMArena WebDev15411447
SciCode54.3%58.9%
GSO37.3%22.6%
WeirdML68.8%72.1%
LMArena Coding14831484
ALE-Bench1,4631,161
SWE-bench Verified—75.6%
FrontierCode42.7%—
CursorBench34.1%—
MirrorCode—8.9%
AlgoTune—2.02

Agentic & Tool Use Claude Sonnet 5 leads

Claude Sonnet 5: 42.8 (#18), Gemini 3.1 Pro Preview: 37.7 (#34)

BenchmarkClaude Sonnet 5Gemini 3.1 Pro Preview
APEX-Agents54.5%35.3%
GBAEval65.3%0.8%
LMArena Search11941211
Vending-Bench 26,3783,774
Terminal-Bench—80.2%
τ²-bench Banking—26%
DeepResearch Bench—47.8%
PostTrainBench—22%
BALROG—57%
ExploitBench—26.1%
GDP.pdf—17%
METR Time Horizons—77%

Reasoning Gemini 3.1 Pro Preview leads

Claude Sonnet 5: 49.1 (#39), Gemini 3.1 Pro Preview: 71.7 (#12)

BenchmarkClaude Sonnet 5Gemini 3.1 Pro Preview
SimpleBench60.6%79.6%
NYT Connections (extended)75.1%97.4%
CritPt16.9%17.7%
Chess Puzzles35%55%
LMArena Hard Prompts14611485
Mystery Game Puzzles35%34%
DTBench92.5%97.1%
LMCA50%53.8%
Epoch Capabilities Index156.21154.77
ForecastBench61.159
ARC-AGI-2—77.1%
ARC-AGI-1—98%
EnigmaEval—36.8%
Thematic Generalization—79.4%
EBR-Bench—14.3%
Surface Evolver Bench60%—
Bench to the Future 30.14—

Math Claude Sonnet 5 leads

Claude Sonnet 5: 66.2 (#27), Gemini 3.1 Pro Preview: 62.1 (#34)

BenchmarkClaude Sonnet 5Gemini 3.1 Pro Preview
FrontierMath (Tiers 1-3)65.6%59.6%
FrontierMath Tier 429.3%26.8%
OTIS Mock AIME 2024-202594.7%95.6%
ProofBench77%26%
LMArena Math14671485
MathArena Final-Answer Competitions—86.5%
FrontierMath (Feb 2025 set)—36.9%
FrontierMath Tier 4 (v1)—16.7%

Knowledge Gemini 3.1 Pro Preview leads

Claude Sonnet 5: 55.6 (#47), Gemini 3.1 Pro Preview: 71.8 (#3)

BenchmarkClaude Sonnet 5Gemini 3.1 Pro Preview
GPQA Diamond90.5%94.4%
SimpleQA Verified33.7%73.5%
LMArena Expert14901485
Humanity's Last Exam—46.4%
Vectara Hallucination Rate—10.4%

Multimodal Claude Sonnet 5 leads

Claude Sonnet 5: 42.4 (#31), Gemini 3.1 Pro Preview: 37.9 (#69)

BenchmarkClaude Sonnet 5Gemini 3.1 Pro Preview
LMArena Vision12741296
Blueprint-Bench 224.9%26.5%
LMArena Document14661444
Furniture Assembly—26.7%

Multilingual Gemini 3.1 Pro Preview leads

Claude Sonnet 5: 53.8 (#55), Gemini 3.1 Pro Preview: 57.0 (#12)

BenchmarkClaude Sonnet 5Gemini 3.1 Pro Preview
LMArena Non-English14311477
LMArena Chinese14771529
LMArena French14601487
LMArena German14401491
LMArena Japanese14221493
LMArena Korean14111455
LMArena Russian14511498
LMArena Spanish14371479

Instruction Following Too close to call

Claude Sonnet 5: 76.3 (#41), Gemini 3.1 Pro Preview: 77.0 (#32)

BenchmarkClaude Sonnet 5Gemini 3.1 Pro Preview
LMArena Instruction Following14521466

Long Context Gemini 3.1 Pro Preview leads

Claude Sonnet 5: 44.8 (#55), Gemini 3.1 Pro Preview: 47.4 (#18)

BenchmarkClaude Sonnet 5Gemini 3.1 Pro Preview
LMArena Longer Query14631483
CL-bench—20.8%
CL-bench Life—16.9%

Writing & Preference Claude Sonnet 5 leads

Claude Sonnet 5: 69.2 (#25), Gemini 3.1 Pro Preview: 66.1 (#37)

BenchmarkClaude Sonnet 5Gemini 3.1 Pro Preview
LMArena Text14421481
LMArena Creative Writing14161482
EQ-Bench Creative Writing17941491
EQ-Bench 412361142
LMArena Multi-Turn14541488

Frequently asked questions

Is Claude Sonnet 5 better than Gemini 3.1 Pro Preview?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 54.6 on the Noometry Index.

Which is cheaper, Claude Sonnet 5 or Gemini 3.1 Pro Preview?

Claude Sonnet 5 is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Claude Sonnet 5 or Gemini 3.1 Pro Preview better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 42.5 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 5 and Gemini 3.1 Pro Preview share?

47 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Gemini 3.1 Pro Preview has 71.

Related comparisons

Go deeper