Noometry

Model comparison

Claude Opus 4.6 vs Gemini 3.8 Flash

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 58.2 on the Noometry Index.

Last verified . 42 shared benchmarks.

Claude Opus 4.6 Anthropic

58.2

Rank #20 Confirmed

Gemini 3.8 Flash Google

61.8

Rank #11 Confirmed

Summary

  • They share 42 benchmarks with published results for both. Claude Opus 4.6 scores higher in 4 categories and Gemini 3.8 Flash in 6 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 57.8.
  • The biggest single-benchmark swing is Chess Puzzles: 17% for Claude Opus 4.6 and 61% for Gemini 3.8 Flash.
  • Gemini 3.8 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $5 / $25 for Claude Opus 4.6.
  • Gemini 3.8 Flash accepts more context: 1.05M tokens versus 1M.

Side by side

Claude Opus 4.6Gemini 3.8 Flash
ProviderAnthropicGoogle
Noometry Index58.261.8
Released2026-02-042026-09-02
WeightsProprietaryProprietary
Context window1M1.05M
Max output128K66K
Input $ / M tokens$5$0.75
Output $ / M tokens$25$3.75
Results tracked6850

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

Category by category

Coding Gemini 3.8 Flash leads

Claude Opus 4.6: 57.2 (#20), Gemini 3.8 Flash: 59.2 (#15)

BenchmarkClaude Opus 4.6Gemini 3.8 Flash
FrontierCode26.6%41.2%
LMArena WebDev15471584
WeirdML78%84.8%
LMArena Coding15361510
ALE-Bench996.51,270
SWE-bench Verified78.7%—
DeepSWE—73.8%
SWE-bench Verified (bash only)75.6%—
CursorBench—39.6%
SWE-bench Multilingual72%—
FrontierSWE—19.6%
SciCode—56.6%
GSO41.2%—
AlgoTune1.47—

Agentic & Tool Use Claude Opus 4.6 leads

Claude Opus 4.6: 51.1 (#4), Gemini 3.8 Flash: 41.8 (#21)

BenchmarkClaude Opus 4.6Gemini 3.8 Flash
APEX-Agents46.3%64.3%
Remote Labor Index4.2%5.8%
Vending-Bench 28,0185,094
Terminal-Bench79.8%—
τ²-bench Banking27.3%—
Cybench93%—
DeepResearch Bench55.3%—
GBAEval44.1%—
GDP.pdf—23.4%
LMArena Search1253—
METR Time Horizons78.9%—

Reasoning Gemini 3.8 Flash leads

Claude Opus 4.6: 57.8 (#23), Gemini 3.8 Flash: 76.9 (#5)

BenchmarkClaude Opus 4.6Gemini 3.8 Flash
ARC-AGI-269.2%89.2%
NYT Connections (extended)92.1%97.4%
ARC-AGI-194%98.5%
Chess Puzzles17%61%
LMArena Hard Prompts15271508
Mystery Game Puzzles25%47%
DTBench91.2%95.7%
LMCA55.8%52.9%
Epoch Capabilities Index155.24156.71
SimpleBench67.6%—
Kagi LLM Benchmark83.6%—
CritPt—18.3%
EnigmaEval7.6%—
Thematic Generalization80.6%—
EBR-Bench12.7%—
Surface Evolver Bench—76.9%
ForecastBench60—

Math Gemini 3.8 Flash leads

Claude Opus 4.6: 63.0 (#31), Gemini 3.8 Flash: 65.3 (#28)

BenchmarkClaude Opus 4.6Gemini 3.8 Flash
FrontierMath (Tiers 1-3)66%68.4%
FrontierMath Tier 426.8%22%
OTIS Mock AIME 2024-202594.4%98.9%
ProofBench50%48%
LMArena Math15191528
MathArena Final-Answer Competitions78.5%—
FrontierMath (Feb 2025 set)40.7%—
FrontierMath Tier 4 (v1)22.9%—

Knowledge Gemini 3.8 Flash leads

Claude Opus 4.6: 61.9 (#26), Gemini 3.8 Flash: 74.8 (#2)

BenchmarkClaude Opus 4.6Gemini 3.8 Flash
GPQA Diamond90.5%95.4%
Humanity's Last Exam34.4%44.5%
SimpleQA Verified47%69.7%
LMArena Expert15461524
Vectara Hallucination Rate12.2%—

Multimodal Gemini 3.8 Flash leads

Claude Opus 4.6: 37.3 (#74), Gemini 3.8 Flash: 40.7 (#45)

BenchmarkClaude Opus 4.6Gemini 3.8 Flash
LMArena Vision13161314
Furniture Assembly28.3%31.7%
Blueprint-Bench 2—38.6%
LMArena Document1507—

Multilingual Too close to call

Claude Opus 4.6: 57.9 (#6), Gemini 3.8 Flash: 58.0 (#5)

BenchmarkClaude Opus 4.6Gemini 3.8 Flash
LMArena Non-English14891491
LMArena Chinese15511554
LMArena French15131498
LMArena German15021493
LMArena Japanese14841502
LMArena Korean14641459
LMArena Russian14971515
LMArena Spanish15101485

Instruction Following Claude Opus 4.6 leads

Claude Opus 4.6: 79.5 (#4), Gemini 3.8 Flash: 78.0 (#13)

BenchmarkClaude Opus 4.6Gemini 3.8 Flash
LMArena Instruction Following15231490

Long Context Claude Opus 4.6 leads

Claude Opus 4.6: 48.1 (#13), Gemini 3.8 Flash: 46.3 (#24)

BenchmarkClaude Opus 4.6Gemini 3.8 Flash
LMArena Longer Query15201508
CL-bench20.7%—
CL-bench Life17%—

Writing & Preference Claude Opus 4.6 leads

Claude Opus 4.6: 73.5 (#10), Gemini 3.8 Flash: 72.2 (#15)

BenchmarkClaude Opus 4.6Gemini 3.8 Flash
LMArena Text15031499
LMArena Creative Writing15051492
EQ-Bench Creative Writing18091748
LMArena Multi-Turn15131501
EQ-Bench 41223—

Frequently asked questions

Is Claude Opus 4.6 better than Gemini 3.8 Flash?

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 58.2 on the Noometry Index.

Which is cheaper, Claude Opus 4.6 or Gemini 3.8 Flash?

Gemini 3.8 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Claude Opus 4.6 lists at $5 and $25.

Is Claude Opus 4.6 or Gemini 3.8 Flash better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 57.2 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.8 Flash does, with 1.05M tokens against 1M.

How many benchmarks do Claude Opus 4.6 and Gemini 3.8 Flash share?

42 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and Gemini 3.8 Flash has 50.

Related comparisons

Go deeper