Model comparison

DeepSeek V4.1 Flash vs Reka Flash 3

DeepSeek V4.1 Flash has enough public results to be ranked (#40); Reka Flash 3 does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

DeepSeek V4.1 Flash DeepSeek

50.3

Rank #40 Confirmed

Reka Flash 3 Reka

36.4

Unranked Sparse

Summary

  • They share 1 benchmark with published results for both. DeepSeek V4.1 Flash scores higher in 1 category and Reka Flash 3 in 0 categories; one gap is clear of the uncertainty.
  • The widest gap is in writing & preference, where DeepSeek V4.1 Flash leads 65.8 to 43.8.
  • Reka Flash 3 is cheaper at $0.10 / $0.20 per million input/output tokens, against $0.15 / $0.60 for DeepSeek V4.1 Flash.
  • DeepSeek V4.1 Flash accepts more context: 1M tokens versus 66K.

Side by side

DeepSeek V4.1 Flash and Reka Flash 3 specifications
DeepSeek V4.1 FlashReka Flash 3
ProviderDeepSeekReka
Noometry Index50.336.4
Released2026-09-092025-03-10
WeightsOpenOpen
Context window1M66K
Max output393K59K
Input $ / M tokens$0.15$0.10
Output $ / M tokens$0.60$0.20
Results tracked252

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

Category by category

Coding Not comparable

DeepSeek V4.1 Flash: 52.8 (#29), Reka Flash 3: —

Coding benchmarks
BenchmarkDeepSeek V4.1 FlashReka Flash 3
LMArena WebDev1620—
SciCode51.9%—
LMArena Coding1511—
ALE-Bench1,092—

Agentic & Tool Use Not comparable

DeepSeek V4.1 Flash: —, Reka Flash 3: 30.1

Agentic & Tool Use benchmarks
BenchmarkDeepSeek V4.1 FlashReka Flash 3
BALROG—29.2%

Reasoning Not comparable

DeepSeek V4.1 Flash: 46.2 (#39), Reka Flash 3: —

Reasoning benchmarks
BenchmarkDeepSeek V4.1 FlashReka Flash 3
NYT Connections (extended)89.6%—
CritPt14.3%—
LMArena Hard Prompts1485—
DTBench89.9%—
LMCA47%—
Surface Evolver Bench46.3%—
Epoch Capabilities Index155.01—

Math Not comparable

DeepSeek V4.1 Flash: 48.4 (#52), Reka Flash 3: —

Math benchmarks
BenchmarkDeepSeek V4.1 FlashReka Flash 3
ProofBench54%—
LMArena Math1493—

Knowledge Not comparable

DeepSeek V4.1 Flash: 41.6 (#97), Reka Flash 3: —

Knowledge benchmarks
BenchmarkDeepSeek V4.1 FlashReka Flash 3
LMArena Expert1505—

Multilingual Not comparable

DeepSeek V4.1 Flash: 55.5 (#29), Reka Flash 3: —

Multilingual benchmarks
BenchmarkDeepSeek V4.1 FlashReka Flash 3
LMArena Non-English1452—
LMArena Chinese1506—
LMArena French1448—
LMArena Russian1473—
LMArena Spanish1499—

Instruction Following Not comparable

DeepSeek V4.1 Flash: 77.6 (#24), Reka Flash 3: —

Instruction Following benchmarks
BenchmarkDeepSeek V4.1 FlashReka Flash 3
LMArena Instruction Following1475—

Long Context Not comparable

DeepSeek V4.1 Flash: 45.2 (#46), Reka Flash 3: —

Long Context benchmarks
BenchmarkDeepSeek V4.1 FlashReka Flash 3
LMArena Longer Query1476—

Writing & Preference DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 65.8 (#43), Reka Flash 3: 43.8

Writing & Preference benchmarks
BenchmarkDeepSeek V4.1 FlashReka Flash 3
EQ-Bench Creative Writing15401228
LMArena Text1465—
LMArena Creative Writing1436—
LMArena Multi-Turn1460—

Frequently asked questions

Is DeepSeek V4.1 Flash better than Reka Flash 3?

DeepSeek V4.1 Flash has enough public results to be ranked (#40); Reka Flash 3 does not yet, so treat this comparison as directional.

Which is cheaper, DeepSeek V4.1 Flash or Reka Flash 3?

Reka Flash 3 is cheaper. It lists at $0.10 per million input tokens and $0.20 per million output tokens; DeepSeek V4.1 Flash lists at $0.15 and $0.60.

Which has the bigger context window?

DeepSeek V4.1 Flash does, with 1M tokens against 66K.

How many benchmarks do DeepSeek V4.1 Flash and Reka Flash 3 share?

1 benchmark has published results for both models. DeepSeek V4.1 Flash has 25 scored results on Noometry and Reka Flash 3 has 2.

Related comparisons

Go deeper