Noometry

Model comparison

Claude Opus 5 vs Gemini 3 Deep Think

Claude Opus 5 has enough public results to be ranked (#4); Gemini 3 Deep Think does not yet, so treat this comparison as directional.

Last verified . 3 shared benchmarks.

Claude Opus 5 Anthropic

67.8

Rank #4 Confirmed

Gemini 3 Deep Think Google

58.3

Unranked Sparse

Summary

  • They share 3 benchmarks with published results for both. Claude Opus 5 scores higher in 1 category and Gemini 3 Deep Think in 0 categories; one gap is clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 5 leads 77.2 to 70.2.
  • The biggest single-benchmark swing is ARC-AGI-2: 90.4% for Claude Opus 5 and 84.6% for Gemini 3 Deep Think.

Side by side

Claude Opus 5Gemini 3 Deep Think
ProviderAnthropicGoogle
Noometry Index67.858.3
Released2026-07-242026-02-12
WeightsProprietaryProprietary
Context window1M—
Max output128K—
Input $ / M tokens$5—
Output $ / M tokens$25—
Results tracked573

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

Category by category

Coding Not comparable

Claude Opus 5: 67.5 (#5), Gemini 3 Deep Think: —

BenchmarkClaude Opus 5Gemini 3 Deep Think
DeepSWE73.6%—
FrontierCode53.4%—
CursorBench46.6%—
LMArena WebDev1691—
FrontierSWE52%—
SciCode56.4%—
WeirdML91.8%—
LMArena Coding1534—
ALE-Bench2,165—

Agentic & Tool Use Not comparable

Claude Opus 5: 55.6 (#1), Gemini 3 Deep Think: —

BenchmarkClaude Opus 5Gemini 3 Deep Think
APEX-Agents65.8%—
OSWorld 2.031.4%—
τ²-bench Banking48.7%—
PostTrainBench35%—
BALROG63.4%—
GBAEval79.6%—
GDP.pdf24%—
Vending-Bench 211,182—

Reasoning Claude Opus 5 leads

Claude Opus 5: 77.2 (#4), Gemini 3 Deep Think: 70.2 (#14)

BenchmarkClaude Opus 5Gemini 3 Deep Think
ARC-AGI-290.4%84.6%
ARC-AGI-197.5%96%
CritPt29.1%25.7%
SimpleBench80.6%—
NYT Connections (extended)94.3%—
Chess Puzzles42%—
EBR-Bench45.7%—
LMArena Hard Prompts1526—
Mystery Game Puzzles59%—
DTBench97.9%—
LMCA64.5%—
Bench to the Future 30.12—
Epoch Capabilities Index162.78—

Math Not comparable

Claude Opus 5: 86.2 (#8), Gemini 3 Deep Think: —

BenchmarkClaude Opus 5Gemini 3 Deep Think
FrontierMath (Tiers 1-3)85.6%—
FrontierMath Tier 473.2%—
OTIS Mock AIME 2024-202598.9%—
ProofBench99%—
LMArena Math1531—

Knowledge Not comparable

Claude Opus 5: 66.8 (#9), Gemini 3 Deep Think: —

BenchmarkClaude Opus 5Gemini 3 Deep Think
GPQA Diamond93.9%—
SimpleQA Verified59.9%—
LMArena Expert1557—

Multimodal Not comparable

Claude Opus 5: 50.8 (#8), Gemini 3 Deep Think: —

BenchmarkClaude Opus 5Gemini 3 Deep Think
LMArena Vision1319—
Blueprint-Bench 230.4%—
Furniture Assembly60.8%—
LMArena Document1516—

Multilingual Not comparable

Claude Opus 5: 58.8 (#4), Gemini 3 Deep Think: —

BenchmarkClaude Opus 5Gemini 3 Deep Think
LMArena Non-English1501—
LMArena Chinese1574—
LMArena French1519—
LMArena German1524—
LMArena Japanese1516—
LMArena Korean1521—
LMArena Russian1507—
LMArena Spanish1519—

Instruction Following Not comparable

Claude Opus 5: 79.2 (#7), Gemini 3 Deep Think: —

BenchmarkClaude Opus 5Gemini 3 Deep Think
LMArena Instruction Following1517—

Long Context Not comparable

Claude Opus 5: 46.5 (#21), Gemini 3 Deep Think: —

BenchmarkClaude Opus 5Gemini 3 Deep Think
LMArena Longer Query1515—

Writing & Preference Not comparable

Claude Opus 5: 79.2 (#1), Gemini 3 Deep Think: —

BenchmarkClaude Opus 5Gemini 3 Deep Think
LMArena Text1507—
LMArena Creative Writing1491—
EQ-Bench Creative Writing2133—
EQ-Bench 41385—
LMArena Multi-Turn1499—

Frequently asked questions

Is Claude Opus 5 better than Gemini 3 Deep Think?

Claude Opus 5 has enough public results to be ranked (#4); Gemini 3 Deep Think does not yet, so treat this comparison as directional.

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

3 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and Gemini 3 Deep Think has 3.

Related comparisons

Go deeper