Noometry

Model comparison

DeepSeek V4.1 Flash vs Gemini 2.5 Pro

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 45.0 on the Noometry Index.

Last verified . 30 shared benchmarks.

DeepSeek V4.1 Flash DeepSeek

52.8

Rank #38 Confirmed

Gemini 2.5 Pro Google

45.0

Rank #75 Confirmed

Summary

  • They share 30 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 7 categories and Gemini 2.5 Pro in 3 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 32.5.
  • The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 67.4% for DeepSeek V4.1 Flash and 24.6% for Gemini 2.5 Pro.
  • DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
  • Gemini 2.5 Pro accepts more context: 1.05M tokens versus 1M.
  • DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.

Side by side

DeepSeek V4.1 FlashGemini 2.5 Pro
ProviderDeepSeekGoogle
Noometry Index52.845.0
Released2026-09-092025-03-25
WeightsOpenProprietary
Context window1M1.05M
Max output393K66K
Input $ / M tokens$0.15$1.25
Output $ / M tokens$0.60$10
Results tracked3778

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

Category by category

Coding DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 52.9 (#32), Gemini 2.5 Pro: 42.4 (#101)

BenchmarkDeepSeek V4.1 FlashGemini 2.5 Pro
LMArena WebDev16191227
SciCode51.9%42.8%
LMArena Coding15061452
ALE-Bench1,092785.52
SWE-bench Verified—57.6%
SWE-bench Verified (bash only)—53.6%
Aider Polyglot—83.1%
GSO—3.9%
WeirdML—54%
LiveBench Coding—85.9%
CadEval—64%
AlgoTune—1.51

Agentic & Tool Use DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 31.2 (#69), Gemini 2.5 Pro: 29.2 (#88)

BenchmarkDeepSeek V4.1 FlashGemini 2.5 Pro
Terminal-Bench—32.6%
APEX-Agents39.5%—
GDPval—23.3%
Remote Labor Index—0.8%
TheAgentCompany—30.3%
τ²-bench Banking—13.7%
DeepResearch Bench—42.8%
BALROG—43.3%
GDP.pdf19.8%—
LMArena Search—1142
METR Time Horizons—55.4%
Vending-Bench 2—573.64

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 50.2 (#36), Gemini 2.5 Pro: 28.8 (#99)

BenchmarkDeepSeek V4.1 FlashGemini 2.5 Pro
CritPt14.3%2%
LMArena Hard Prompts14831455
DTBench89.9%82.4%
LMCA47%34.8%
Epoch Capabilities Index154.9145.32
ARC-AGI-2—4.9%
SimpleBench—62.4%
Kagi LLM Benchmark—70.3%
NYT Connections (extended)89.6%—
ARC-AGI-1—41%
Chess Puzzles—20%
EnigmaEval—5.6%
LiveBench Reasoning—89.8%
Mystery Game Puzzles43%—
LiveBench Data Analysis—79.9%
Surface Evolver Bench46.3%—
ForecastBench—61.3
LiveBench—82.3%

Math DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 66.7 (#25), Gemini 2.5 Pro: 32.5 (#213)

BenchmarkDeepSeek V4.1 FlashGemini 2.5 Pro
FrontierMath (Tiers 1-3)67.4%24.6%
FrontierMath Tier 426.8%0%
OTIS Mock AIME 2024-202598.3%84.7%
LMArena Math14771450
ProofBench54%—
Omni-MATH—41.6%
LiveBench Math—90.2%
MATH Level 5—95.9%
FrontierMath (Feb 2025 set)—14.1%
FrontierMath Tier 4 (v1)—4.2%

Knowledge DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 57.9 (#38), Gemini 2.5 Pro: 56.0 (#46)

BenchmarkDeepSeek V4.1 FlashGemini 2.5 Pro
GPQA Diamond89.8%85.3%
LMArena Expert15061452
Humanity's Last Exam—21.6%
MMLU-Pro—86.3%
Confabulations—10.6%
Vectara Hallucination Rate—7%
GPQA (HELM)—74.9%

Multimodal Gemini 2.5 Pro leads

DeepSeek V4.1 Flash: 39.1 (#61), Gemini 2.5 Pro: 45.2 (#18)

BenchmarkDeepSeek V4.1 FlashGemini 2.5 Pro
LMArena Vision12771263
GeoBench—86%
VPCT—48%
Furniture Assembly34.2%—
LMArena Document—1421
SpatialViz-Bench—44.7%

Multilingual Too close to call

DeepSeek V4.1 Flash: 55.0 (#35), Gemini 2.5 Pro: 55.3 (#31)

BenchmarkDeepSeek V4.1 FlashGemini 2.5 Pro
LMArena Non-English14481451
LMArena Chinese14971507
LMArena French14521472
LMArena German14841487
LMArena Japanese14121461
LMArena Korean14521434
LMArena Russian14711461
LMArena Spanish14591473

Instruction Following DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 77.3 (#26), Gemini 2.5 Pro: 75.0 (#75)

BenchmarkDeepSeek V4.1 FlashGemini 2.5 Pro
LMArena Instruction Following14741437
LiveBench Instruction Following—80.6%
IFEval—84%

Long Context Gemini 2.5 Pro leads

DeepSeek V4.1 Flash: 45.2 (#47), Gemini 2.5 Pro: 59.8 (#5)

BenchmarkDeepSeek V4.1 FlashGemini 2.5 Pro
LMArena Longer Query14751449
Fiction.LiveBench—91.7%

Writing & Preference DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 65.4 (#48), Gemini 2.5 Pro: 63.7 (#62)

BenchmarkDeepSeek V4.1 FlashGemini 2.5 Pro
LMArena Text14621458
LMArena Creative Writing14351454
EQ-Bench Creative Writing15401421
LMArena Multi-Turn14571453
Short-Story Creative Writing—83.8%
WildBench—85.7%
LiveBench Language—67.8%

Frequently asked questions

Is DeepSeek V4.1 Flash better than Gemini 2.5 Pro?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 45.0 on the Noometry Index.

Which is cheaper, DeepSeek V4.1 Flash or Gemini 2.5 Pro?

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

Is DeepSeek V4.1 Flash or Gemini 2.5 Pro better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 42.4 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 1M.

How many benchmarks do DeepSeek V4.1 Flash and Gemini 2.5 Pro share?

30 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Gemini 2.5 Pro has 78.

Related comparisons

Go deeper