Noometry

Model comparison

Claude Opus 5 vs Gemini 3.1 Pro Preview

Claude Opus 5 is the stronger model overall, scoring 67.8 to 56.7 on the Noometry Index. Gemini 3.1 Pro Preview costs 2.2× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.

Last verified . 52 shared benchmarks.

Claude Opus 5 Anthropic

67.8

Rank #4 Confirmed

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

Summary

  • They share 52 benchmarks with published results for both. Claude Opus 5 scores higher in 8 categories and Gemini 3.1 Pro Preview in 2 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Claude Opus 5 leads 67.5 to 42.5.
  • The biggest single-benchmark swing is GBAEval: 79.6% for Claude Opus 5 and 0.8% for Gemini 3.1 Pro Preview.
  • Gemini 3.1 Pro Preview is cheaper at $2 / $12 per million input/output tokens, against $5 / $25 for Claude Opus 5.
  • Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 1M.

Side by side

Claude Opus 5Gemini 3.1 Pro Preview
ProviderAnthropicGoogle
Noometry Index67.856.7
Released2026-07-242026-02-19
WeightsProprietaryProprietary
Context window1M1.05M
Max output128K66K
Input $ / M tokens$5$2
Output $ / M tokens$25$12
Results tracked5771

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

Category by category

Coding Claude Opus 5 leads

Claude Opus 5: 67.5 (#5), Gemini 3.1 Pro Preview: 42.5 (#99)

BenchmarkClaude Opus 5Gemini 3.1 Pro Preview
DeepSWE73.6%11.7%
LMArena WebDev16911447
SciCode56.4%58.9%
WeirdML91.8%72.1%
LMArena Coding15341484
ALE-Bench2,1651,161
SWE-bench Verified—75.6%
FrontierCode53.4%—
CursorBench46.6%—
FrontierSWE52%—
GSO—22.6%
MirrorCode—8.9%
AlgoTune—2.02

Agentic & Tool Use Claude Opus 5 leads

Claude Opus 5: 55.6 (#1), Gemini 3.1 Pro Preview: 37.7 (#34)

BenchmarkClaude Opus 5Gemini 3.1 Pro Preview
APEX-Agents65.8%35.3%
τ²-bench Banking48.7%26%
PostTrainBench35%22%
BALROG63.4%57%
GBAEval79.6%0.8%
GDP.pdf24%17%
Vending-Bench 211,1823,774
Terminal-Bench—80.2%
OSWorld 2.031.4%—
DeepResearch Bench—47.8%
ExploitBench—26.1%
LMArena Search—1211
METR Time Horizons—77%

Reasoning Claude Opus 5 leads

Claude Opus 5: 77.2 (#4), Gemini 3.1 Pro Preview: 71.7 (#12)

BenchmarkClaude Opus 5Gemini 3.1 Pro Preview
ARC-AGI-290.4%77.1%
SimpleBench80.6%79.6%
NYT Connections (extended)94.3%97.4%
ARC-AGI-197.5%98%
CritPt29.1%17.7%
Chess Puzzles42%55%
EBR-Bench45.7%14.3%
LMArena Hard Prompts15261485
Mystery Game Puzzles59%34%
DTBench97.9%97.1%
LMCA64.5%53.8%
Epoch Capabilities Index162.78154.77
EnigmaEval—36.8%
Thematic Generalization—79.4%
Bench to the Future 30.12—
ForecastBench—59

Math Claude Opus 5 leads

Claude Opus 5: 86.2 (#8), Gemini 3.1 Pro Preview: 62.1 (#34)

BenchmarkClaude Opus 5Gemini 3.1 Pro Preview
FrontierMath (Tiers 1-3)85.6%59.6%
FrontierMath Tier 473.2%26.8%
OTIS Mock AIME 2024-202598.9%95.6%
ProofBench99%26%
LMArena Math15311485
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 Opus 5: 66.8 (#9), Gemini 3.1 Pro Preview: 71.8 (#3)

BenchmarkClaude Opus 5Gemini 3.1 Pro Preview
GPQA Diamond93.9%94.4%
SimpleQA Verified59.9%73.5%
LMArena Expert15571485
Humanity's Last Exam—46.4%
Vectara Hallucination Rate—10.4%

Multimodal Claude Opus 5 leads

Claude Opus 5: 50.8 (#8), Gemini 3.1 Pro Preview: 37.9 (#69)

BenchmarkClaude Opus 5Gemini 3.1 Pro Preview
LMArena Vision13191296
Blueprint-Bench 230.4%26.5%
Furniture Assembly60.8%26.7%
LMArena Document15161444

Multilingual Claude Opus 5 leads

Claude Opus 5: 58.8 (#4), Gemini 3.1 Pro Preview: 57.0 (#12)

BenchmarkClaude Opus 5Gemini 3.1 Pro Preview
LMArena Non-English15011477
LMArena Chinese15741529
LMArena French15191487
LMArena German15241491
LMArena Japanese15161493
LMArena Korean15211455
LMArena Russian15071498
LMArena Spanish15191479

Instruction Following Claude Opus 5 leads

Claude Opus 5: 79.2 (#7), Gemini 3.1 Pro Preview: 77.0 (#32)

BenchmarkClaude Opus 5Gemini 3.1 Pro Preview
LMArena Instruction Following15171466

Long Context Too close to call

Claude Opus 5: 46.5 (#21), Gemini 3.1 Pro Preview: 47.4 (#18)

BenchmarkClaude Opus 5Gemini 3.1 Pro Preview
LMArena Longer Query15151483
CL-bench—20.8%
CL-bench Life—16.9%

Writing & Preference Claude Opus 5 leads

Claude Opus 5: 79.2 (#1), Gemini 3.1 Pro Preview: 66.1 (#37)

BenchmarkClaude Opus 5Gemini 3.1 Pro Preview
LMArena Text15071481
LMArena Creative Writing14911482
EQ-Bench Creative Writing21331491
EQ-Bench 413851142
LMArena Multi-Turn14991488

Frequently asked questions

Is Claude Opus 5 better than Gemini 3.1 Pro Preview?

Claude Opus 5 is the stronger model overall, scoring 67.8 to 56.7 on the Noometry Index. Gemini 3.1 Pro Preview costs 2.2× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 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 Opus 5 lists at $5 and $25.

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

Claude Opus 5 scores higher on coding benchmarks: 67.5 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 Opus 5 and Gemini 3.1 Pro Preview share?

52 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and Gemini 3.1 Pro Preview has 71.

Related comparisons

Go deeper