Noometry

Model comparison

Claude Opus 4.5 vs Gemini 2.5 Pro

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 45.0 on the Noometry Index. Gemini 2.5 Pro costs 2.9× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Last verified . 55 shared benchmarks.

Claude Opus 4.5 Anthropic

50.5

Rank #47 Confirmed

Gemini 2.5 Pro Google

45.0

Rank #75 Confirmed

Summary

  • They share 55 benchmarks with published results for both. Claude Opus 4.5 scores higher in 7 categories and Gemini 2.5 Pro in 3 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where Claude Opus 4.5 leads 47.3 to 29.2.
  • The biggest single-benchmark swing is ARC-AGI-1: 80% for Claude Opus 4.5 and 41% for Gemini 2.5 Pro.
  • Gemini 2.5 Pro is cheaper at $1.25 / $10 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
  • Gemini 2.5 Pro accepts more context: 1.05M tokens versus 200K.

Side by side

Claude Opus 4.5Gemini 2.5 Pro
ProviderAnthropicGoogle
Noometry Index50.545.0
Released2025-11-012025-03-25
WeightsProprietaryProprietary
Context window200K1.05M
Max output64K66K
Input $ / M tokens$5$1.25
Output $ / M tokens$25$10
Results tracked6978

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

Category by category

Coding Claude Opus 4.5 leads

Claude Opus 4.5: 54.8 (#27), Gemini 2.5 Pro: 42.4 (#101)

BenchmarkClaude Opus 4.5Gemini 2.5 Pro
SWE-bench Verified76.7%57.6%
SWE-bench Verified (bash only)76.8%53.6%
LMArena WebDev14941227
GSO26.5%3.9%
WeirdML63.7%54%
LMArena Coding15041452
ALE-Bench1,025785.52
AlgoTune1.771.51
Aider Polyglot—83.1%
SWE-bench Multilingual70.7%—
SciCode—42.8%
LiveBench Coding—85.9%
CadEval—64%

Agentic & Tool Use Claude Opus 4.5 leads

Claude Opus 4.5: 47.3 (#12), Gemini 2.5 Pro: 29.2 (#88)

BenchmarkClaude Opus 4.5Gemini 2.5 Pro
Terminal-Bench63.1%32.6%
GDPval45.5%23.3%
Remote Labor Index3.8%0.8%
τ²-bench Banking24.7%13.7%
DeepResearch Bench54.8%42.8%
BALROG43.5%43.3%
LMArena Search11801142
METR Time Horizons75%55.4%
Vending-Bench 24,967573.64
Berkeley Function Calling Leaderboard77.5%—
TheAgentCompany—30.3%
τ²-bench Airline84%—
τ²-bench Retail79.6%—
τ²-bench Telecom92.3%—
Cybench82%—
OSWorld66.3%—

Reasoning Claude Opus 4.5 leads

Claude Opus 4.5: 42.6 (#51), Gemini 2.5 Pro: 28.8 (#99)

BenchmarkClaude Opus 4.5Gemini 2.5 Pro
ARC-AGI-237.6%4.9%
SimpleBench62%62.4%
Kagi LLM Benchmark80.2%70.3%
ARC-AGI-180%41%
Chess Puzzles12%20%
EnigmaEval11.9%5.6%
LMArena Hard Prompts14761455
DTBench89.9%82.4%
LMCA44.5%34.8%
Epoch Capabilities Index150.09145.32
ForecastBench60.761.3
NYT Connections (extended)52.5%—
CritPt—2%
EBR-Bench14.3%—
LiveBench Reasoning—89.8%
Mystery Game Puzzles22%—
LiveBench Data Analysis—79.9%
LiveBench—82.3%

Math Claude Opus 4.5 leads

Claude Opus 4.5: 38.6 (#132), Gemini 2.5 Pro: 32.5 (#213)

BenchmarkClaude Opus 4.5Gemini 2.5 Pro
FrontierMath (Tiers 1-3)34.4%24.6%
FrontierMath Tier 44.9%0%
OTIS Mock AIME 2024-202586.1%84.7%
LMArena Math14631450
FrontierMath (Feb 2025 set)20.7%14.1%
FrontierMath Tier 4 (v1)4.2%4.2%
ProofBench36%—
Omni-MATH—41.6%
LiveBench Math—90.2%
MATH Level 5—95.9%

Knowledge Too close to call

Claude Opus 4.5: 56.5 (#44), Gemini 2.5 Pro: 56.0 (#46)

BenchmarkClaude Opus 4.5Gemini 2.5 Pro
GPQA Diamond86%85.3%
Humanity's Last Exam25.2%21.6%
Vectara Hallucination Rate10.9%7%
LMArena Expert14871452
SimpleQA Verified45.7%—
MMLU-Pro—86.3%
Confabulations—10.6%
GPQA (HELM)—74.9%

Multimodal Gemini 2.5 Pro leads

Claude Opus 4.5: 31.4 (#107), Gemini 2.5 Pro: 45.2 (#18)

BenchmarkClaude Opus 4.5Gemini 2.5 Pro
GeoBench75%86%
VPCT40%48%
LMArena Document14621421
LMArena Vision—1263
Furniture Assembly28.3%—
SpatialViz-Bench—44.7%

Multilingual Too close to call

Claude Opus 4.5: 54.3 (#47), Gemini 2.5 Pro: 55.3 (#31)

BenchmarkClaude Opus 4.5Gemini 2.5 Pro
LMArena Non-English14381451
LMArena Chinese14701507
LMArena French14711472
LMArena German14491487
LMArena Japanese14161461
LMArena Korean14241434
LMArena Russian14471461
LMArena Spanish14581473

Instruction Following Claude Opus 4.5 leads

Claude Opus 4.5: 77.5 (#19), Gemini 2.5 Pro: 75.0 (#75)

BenchmarkClaude Opus 4.5Gemini 2.5 Pro
LMArena Instruction Following14781437
LiveBench Instruction Following—80.6%
IFEval—84%

Long Context Gemini 2.5 Pro leads

Claude Opus 4.5: 46.5 (#22), Gemini 2.5 Pro: 59.8 (#5)

BenchmarkClaude Opus 4.5Gemini 2.5 Pro
LMArena Longer Query14801449
Fiction.LiveBench—91.7%
CL-bench21.1%—

Writing & Preference Claude Opus 4.5 leads

Claude Opus 4.5: 68.1 (#28), Gemini 2.5 Pro: 63.7 (#62)

BenchmarkClaude Opus 4.5Gemini 2.5 Pro
LMArena Text14511458
LMArena Creative Writing14451454
EQ-Bench Creative Writing16871421
LMArena Multi-Turn14661453
Short-Story Creative Writing—83.8%
WildBench—85.7%
LiveBench Language—67.8%

Frequently asked questions

Is Claude Opus 4.5 better than Gemini 2.5 Pro?

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 45.0 on the Noometry Index. Gemini 2.5 Pro costs 2.9× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.5 or Gemini 2.5 Pro?

Gemini 2.5 Pro is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; Claude Opus 4.5 lists at $5 and $25.

Is Claude Opus 4.5 or Gemini 2.5 Pro better for coding?

Claude Opus 4.5 scores higher on coding benchmarks: 54.8 versus 42.4 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 200K.

How many benchmarks do Claude Opus 4.5 and Gemini 2.5 Pro share?

55 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and Gemini 2.5 Pro has 78.

Related comparisons

Go deeper