Noometry

Model comparison

Claude Opus 4.7 vs Gemini 3.6 Flash

Claude Opus 4.7 is the stronger model overall, scoring 58.4 to 54.1 on the Noometry Index. Gemini 3.6 Flash costs 6.7× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

Last verified . 45 shared benchmarks.

Claude Opus 4.7 Anthropic

58.4

Rank #17 Confirmed

Gemini 3.6 Flash Google

54.1

Rank #30 Confirmed

Summary

  • They share 45 benchmarks with published results for both. Claude Opus 4.7 scores higher in 8 categories and Gemini 3.6 Flash in 2 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where Claude Opus 4.7 leads 47.9 to 32.4.
  • The biggest single-benchmark swing is NYT Connections (extended): 39% for Claude Opus 4.7 and 89% for Gemini 3.6 Flash.
  • Gemini 3.6 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $5 / $25 for Claude Opus 4.7.
  • Gemini 3.6 Flash accepts more context: 1.05M tokens versus 1M.

Side by side

Claude Opus 4.7Gemini 3.6 Flash
ProviderAnthropicGoogle
Noometry Index58.454.1
Released2026-04-142026-07-21
WeightsProprietaryProprietary
Context window1M1.05M
Max output128K66K
Input $ / M tokens$5$0.75
Output $ / M tokens$25$3.75
Results tracked6646

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: 59.9 (#10), Gemini 3.6 Flash: 49.6 (#45)

BenchmarkClaude Opus 4.7Gemini 3.6 Flash
FrontierCode38.5%34.4%
LMArena WebDev15571536
SciCode54.5%52.7%
WeirdML76.4%56.1%
LMArena Coding15191492
ALE-Bench1,323715.52
SWE-bench Verified83.5%—
DeepSWE—46.7%
GSO44.1%—
MirrorCode31.1%—

Agentic & Tool Use Claude Opus 4.7 leads

Claude Opus 4.7: 47.9 (#8), Gemini 3.6 Flash: 32.4 (#56)

BenchmarkClaude Opus 4.7Gemini 3.6 Flash
APEX-Agents49.2%46.9%
GDP.pdf21%14%
Terminal-Bench80.2%—
OSWorld 2.018.2%—
τ²-bench Banking40.2%—
PostTrainBench28.6%—
ExploitBench26.5%—
GBAEval43.8%—
LMArena Search1233—
Vending-Bench 210,937—

Reasoning Gemini 3.6 Flash leads

Claude Opus 4.7: 53.7 (#24), Gemini 3.6 Flash: 58.9 (#20)

BenchmarkClaude Opus 4.7Gemini 3.6 Flash
ARC-AGI-275.8%60.4%
NYT Connections (extended)39%89%
ARC-AGI-193.5%91.2%
CritPt12%10.6%
Chess Puzzles30%43%
LMArena Hard Prompts15071486
Mystery Game Puzzles28%30%
DTBench94.7%95.5%
LMCA52.2%44.9%
Epoch Capabilities Index156.39154.36
SimpleBench61.7%—
Kagi LLM Benchmark80.7%—
Thematic Generalization72.8%—
EBR-Bench19%—
ForecastBench60.3—

Math Claude Opus 4.7 leads

Claude Opus 4.7: 66.5 (#20), Gemini 3.6 Flash: 57.0 (#33)

BenchmarkClaude Opus 4.7Gemini 3.6 Flash
FrontierMath (Tiers 1-3)70.2%58.9%
FrontierMath Tier 431.7%22%
MathArena Final-Answer Competitions73.6%70.8%
OTIS Mock AIME 2024-202597.8%94.2%
ProofBench54%36%
LMArena Math14991504
FrontierMath (Feb 2025 set)43.8%—
FrontierMath Tier 4 (v1)22.9%—

Knowledge Gemini 3.6 Flash leads

Claude Opus 4.7: 62.6 (#20), Gemini 3.6 Flash: 67.8 (#7)

BenchmarkClaude Opus 4.7Gemini 3.6 Flash
GPQA Diamond90.2%94.1%
SimpleQA Verified51.7%66.2%
LMArena Expert15211489
Humanity's Last Exam36.2%—
Vectara Hallucination Rate12%—

Multimodal Claude Opus 4.7 leads

Claude Opus 4.7: 41.5 (#29), Gemini 3.6 Flash: 38.7 (#55)

BenchmarkClaude Opus 4.7Gemini 3.6 Flash
LMArena Vision13171297
Blueprint-Bench 224.5%31.2%
Furniture Assembly33.3%23.3%
LMArena Document14951456

Multilingual Too close to call

Claude Opus 4.7: 57.5 (#9), Gemini 3.6 Flash: 56.8 (#17)

BenchmarkClaude Opus 4.7Gemini 3.6 Flash
LMArena Non-English14811470
LMArena Chinese15301530
LMArena French15051501
LMArena German14941478
LMArena Japanese14721477
LMArena Korean14661435
LMArena Russian14941490
LMArena Spanish14971477

Instruction Following Claude Opus 4.7 leads

Claude Opus 4.7: 78.6 (#9), Gemini 3.6 Flash: 77.2 (#27)

BenchmarkClaude Opus 4.7Gemini 3.6 Flash
LMArena Instruction Following14981467

Long Context Claude Opus 4.7 leads

Claude Opus 4.7: 46.1 (#24), Gemini 3.6 Flash: 45.1 (#47)

BenchmarkClaude Opus 4.7Gemini 3.6 Flash
LMArena Longer Query15051475

Writing & Preference Claude Opus 4.7 leads

Claude Opus 4.7: 75.3 (#8), Gemini 3.6 Flash: 68.3 (#26)

BenchmarkClaude Opus 4.7Gemini 3.6 Flash
LMArena Text14911478
LMArena Creative Writing14861464
EQ-Bench Creative Writing19141604
LMArena Multi-Turn15061481
EQ-Bench 41311—

Frequently asked questions

Is Claude Opus 4.7 better than Gemini 3.6 Flash?

Claude Opus 4.7 is the stronger model overall, scoring 58.4 to 54.1 on the Noometry Index. Gemini 3.6 Flash costs 6.7× 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 3.6 Flash?

Gemini 3.6 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Claude Opus 4.7 lists at $5 and $25.

Is Claude Opus 4.7 or Gemini 3.6 Flash better for coding?

Claude Opus 4.7 scores higher on coding benchmarks: 59.9 versus 49.6 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.6 Flash does, with 1.05M tokens against 1M.

How many benchmarks do Claude Opus 4.7 and Gemini 3.6 Flash share?

45 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and Gemini 3.6 Flash has 46.

Related comparisons

Go deeper