Noometry

Model comparison

Claude Sonnet 5 vs Gemini 3 Deep Think

Claude Sonnet 5 has enough public results to be ranked (#26); Gemini 3 Deep Think does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

Claude Sonnet 5 Anthropic

54.5

Rank #26 Confirmed

Gemini 3 Deep Think Google

58.5

Unranked Sparse

Summary

  • They share 1 benchmark with published results for both. Claude Sonnet 5 scores higher in 0 categories and Gemini 3 Deep Think in 1 category; one gap is clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3 Deep Think leads 70.8 to 48.2.
  • The biggest single-benchmark swing is CritPt: 16.9% for Claude Sonnet 5 and 25.7% for Gemini 3 Deep Think.

Side by side

Claude Sonnet 5Gemini 3 Deep Think
ProviderAnthropicGoogle
Noometry Index54.558.5
Released2026-06-292026-02-12
WeightsProprietaryProprietary
Context window1M—
Max output128K—
Input $ / M tokens$2—
Output $ / M tokens$10—
Results tracked513

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

Category by category

Coding Not comparable

Claude Sonnet 5: 55.5 (#20), Gemini 3 Deep Think: —

BenchmarkClaude Sonnet 5Gemini 3 Deep Think
DeepSWE53.8%—
FrontierCode42.7%—
CursorBench34.1%—
LMArena WebDev1540—
SciCode53.6%—
GSO37.3%—
WeirdML68.8%—
LMArena Coding1483—
ALE-Bench1,463—

Agentic & Tool Use Not comparable

Claude Sonnet 5: 42.7 (#16), Gemini 3 Deep Think: —

BenchmarkClaude Sonnet 5Gemini 3 Deep Think
APEX-Agents54.5%—
GBAEval65.3%—
LMArena Search1194—
Vending-Bench 26,378—

Reasoning Gemini 3 Deep Think leads

Claude Sonnet 5: 48.2 (#37), Gemini 3 Deep Think: 70.8 (#11)

BenchmarkClaude Sonnet 5Gemini 3 Deep Think
CritPt16.9%25.7%
ARC-AGI-2—84.6%
SimpleBench60.6%—
NYT Connections (extended)75.1%—
ARC-AGI-1—96%
Chess Puzzles35%—
LMArena Hard Prompts1461—
Mystery Game Puzzles35%—
DTBench92.5%—
LMCA50%—
Surface Evolver Bench60%—
Bench to the Future 30.14—
Epoch Capabilities Index156.34—
ForecastBench61.1—

Math Not comparable

Claude Sonnet 5: 66.1 (#21), Gemini 3 Deep Think: —

BenchmarkClaude Sonnet 5Gemini 3 Deep Think
FrontierMath (Tiers 1-3)65.6%—
FrontierMath Tier 429.3%—
OTIS Mock AIME 2024-202594.7%—
ProofBench77%—
LMArena Math1467—

Knowledge Not comparable

Claude Sonnet 5: 55.7 (#42), Gemini 3 Deep Think: —

BenchmarkClaude Sonnet 5Gemini 3 Deep Think
GPQA Diamond90.5%—
SimpleQA Verified33.7%—
LMArena Expert1491—

Multimodal Not comparable

Claude Sonnet 5: 42.4 (#26), Gemini 3 Deep Think: —

BenchmarkClaude Sonnet 5Gemini 3 Deep Think
LMArena Vision1275—
Blueprint-Bench 224.9%—
LMArena Document1466—

Multilingual Not comparable

Claude Sonnet 5: 54.0 (#55), Gemini 3 Deep Think: —

BenchmarkClaude Sonnet 5Gemini 3 Deep Think
LMArena Non-English1431—
LMArena Chinese1475—
LMArena French1457—
LMArena German1448—
LMArena Japanese1422—
LMArena Korean1411—
LMArena Russian1452—
LMArena Spanish1436—

Instruction Following Not comparable

Claude Sonnet 5: 76.6 (#39), Gemini 3 Deep Think: —

BenchmarkClaude Sonnet 5Gemini 3 Deep Think
LMArena Instruction Following1453—

Long Context Not comparable

Claude Sonnet 5: 44.8 (#53), Gemini 3 Deep Think: —

BenchmarkClaude Sonnet 5Gemini 3 Deep Think
LMArena Longer Query1464—

Writing & Preference Not comparable

Claude Sonnet 5: 69.4 (#24), Gemini 3 Deep Think: —

BenchmarkClaude Sonnet 5Gemini 3 Deep Think
LMArena Text1443—
LMArena Creative Writing1416—
EQ-Bench Creative Writing1794—
EQ-Bench 41236—
LMArena Multi-Turn1454—

Frequently asked questions

Is Claude Sonnet 5 better than Gemini 3 Deep Think?

Claude Sonnet 5 has enough public results to be ranked (#26); Gemini 3 Deep Think does not yet, so treat this comparison as directional.

How many benchmarks do Claude Sonnet 5 and Gemini 3 Deep Think share?

1 benchmark has published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Gemini 3 Deep Think has 3.

Related comparisons

Go deeper