Noometry

Model comparison

Claude Opus 4.7 vs Gemini 3.5 Flash

Claude Opus 4.7 is the stronger model overall, scoring 58.3 to 54.2 on the Noometry Index. Gemini 3.5 Flash costs 3.0× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

Last verified . 51 shared benchmarks.

Claude Opus 4.7 Anthropic

58.3

Rank #19 Confirmed

Gemini 3.5 Flash Google

54.2

Rank #32 Confirmed

Summary

  • They share 51 benchmarks with published results for both. Claude Opus 4.7 scores higher in 7 categories and Gemini 3.5 Flash in 3 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where Claude Opus 4.7 leads 47.9 to 24.7.
  • The biggest single-benchmark swing is NYT Connections (extended): 39% for Claude Opus 4.7 and 92.6% for Gemini 3.5 Flash.
  • Gemini 3.5 Flash is cheaper at $1.50 / $9 per million input/output tokens, against $5 / $25 for Claude Opus 4.7.
  • Gemini 3.5 Flash accepts more context: 1.05M tokens versus 1M.

Side by side

Claude Opus 4.7Gemini 3.5 Flash
ProviderAnthropicGoogle
Noometry Index58.354.2
Released2026-04-142026-05-19
WeightsProprietaryProprietary
Context window1M1.05M
Max output128K66K
Input $ / M tokens$5$1.50
Output $ / M tokens$25$9
Results tracked6654

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

Category by category

Coding Claude Opus 4.7 leads

Claude Opus 4.7: 59.6 (#13), Gemini 3.5 Flash: 49.4 (#49)

BenchmarkClaude Opus 4.7Gemini 3.5 Flash
SWE-bench Verified83.5%79.3%
LMArena WebDev15581499
SciCode54.5%53.1%
WeirdML76.4%62.6%
LMArena Coding15181492
ALE-Bench1,323911.02
DeepSWE—37.4%
FrontierCode38.5%—
GSO44.1%—
MirrorCode31.1%—

Agentic & Tool Use Claude Opus 4.7 leads

Claude Opus 4.7: 47.9 (#10), Gemini 3.5 Flash: 24.7 (#114)

BenchmarkClaude Opus 4.7Gemini 3.5 Flash
APEX-Agents49.2%27.5%
GBAEval43.8%6.7%
GDP.pdf21%14%
Vending-Bench 210,9375,396
Terminal-Bench80.2%—
OSWorld 2.018.2%—
τ²-bench Banking40.2%—
PostTrainBench28.6%—
ExploitBench26.5%—
LMArena Search1233—

Reasoning Gemini 3.5 Flash leads

Claude Opus 4.7: 53.8 (#29), Gemini 3.5 Flash: 62.8 (#18)

BenchmarkClaude Opus 4.7Gemini 3.5 Flash
ARC-AGI-275.8%72.1%
SimpleBench61.7%76.7%
NYT Connections (extended)39%92.6%
ARC-AGI-193.5%92.5%
CritPt12%13.1%
Chess Puzzles30%50%
EBR-Bench19%4.8%
LMArena Hard Prompts15061488
Mystery Game Puzzles28%32%
DTBench94.7%94.7%
LMCA52.2%47.1%
Epoch Capabilities Index156.25154.46
ForecastBench60.359
Kagi LLM Benchmark80.7%—
EnigmaEval—25.4%
Thematic Generalization72.8%—
Surface Evolver Bench—58.1%

Math Claude Opus 4.7 leads

Claude Opus 4.7: 66.7 (#26), Gemini 3.5 Flash: 60.7 (#36)

BenchmarkClaude Opus 4.7Gemini 3.5 Flash
FrontierMath (Tiers 1-3)70.2%62.8%
FrontierMath Tier 431.7%26.8%
MathArena Final-Answer Competitions73.6%76.3%
OTIS Mock AIME 2024-202597.8%95.6%
ProofBench54%31%
LMArena Math14991504
FrontierMath (Feb 2025 set)43.8%39%
FrontierMath Tier 4 (v1)22.9%14.6%

Knowledge Gemini 3.5 Flash leads

Claude Opus 4.7: 62.6 (#23), Gemini 3.5 Flash: 66.3 (#11)

BenchmarkClaude Opus 4.7Gemini 3.5 Flash
GPQA Diamond90.2%92.8%
SimpleQA Verified51.7%66.2%
LMArena Expert15211495
Humanity's Last Exam36.2%—
Vectara Hallucination Rate12%—

Multimodal Gemini 3.5 Flash leads

Claude Opus 4.7: 41.2 (#38), Gemini 3.5 Flash: 45.7 (#15)

BenchmarkClaude Opus 4.7Gemini 3.5 Flash
LMArena Vision13161310
Blueprint-Bench 224.5%33.6%
LMArena Document14951463
Furniture Assembly33.3%—

Multilingual Too close to call

Claude Opus 4.7: 57.3 (#10), Gemini 3.5 Flash: 57.0 (#13)

BenchmarkClaude Opus 4.7Gemini 3.5 Flash
LMArena Non-English14801476
LMArena Chinese15311526
LMArena French15031490
LMArena German14951492
LMArena Japanese14721486
LMArena Korean14641451
LMArena Russian14941493
LMArena Spanish14951480

Instruction Following Claude Opus 4.7 leads

Claude Opus 4.7: 78.4 (#10), Gemini 3.5 Flash: 77.0 (#30)

BenchmarkClaude Opus 4.7Gemini 3.5 Flash
LMArena Instruction Following14981467

Long Context Too close to call

Claude Opus 4.7: 46.2 (#25), Gemini 3.5 Flash: 45.4 (#38)

BenchmarkClaude Opus 4.7Gemini 3.5 Flash
LMArena Longer Query15051482

Writing & Preference Claude Opus 4.7 leads

Claude Opus 4.7: 75.1 (#8), Gemini 3.5 Flash: 65.5 (#47)

BenchmarkClaude Opus 4.7Gemini 3.5 Flash
LMArena Text14901482
LMArena Creative Writing14861470
EQ-Bench 413111087
LMArena Multi-Turn15051481
EQ-Bench Creative Writing1914—

Frequently asked questions

Is Claude Opus 4.7 better than Gemini 3.5 Flash?

Claude Opus 4.7 is the stronger model overall, scoring 58.3 to 54.2 on the Noometry Index. Gemini 3.5 Flash costs 3.0× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.7 or Gemini 3.5 Flash?

Gemini 3.5 Flash is cheaper. It lists at $1.50 per million input tokens and $9 per million output tokens; Claude Opus 4.7 lists at $5 and $25.

Is Claude Opus 4.7 or Gemini 3.5 Flash better for coding?

Claude Opus 4.7 scores higher on coding benchmarks: 59.6 versus 49.4 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.5 Flash does, with 1.05M tokens against 1M.

How many benchmarks do Claude Opus 4.7 and Gemini 3.5 Flash share?

51 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and Gemini 3.5 Flash has 54.

Related comparisons

Go deeper