Noometry

Model comparison

Qwen3.6 Max Preview vs Reka Flash 3

Qwen3.6 Max Preview has enough public results to be ranked (#36); Reka Flash 3 does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Qwen3.6 Max Preview Alibaba (Qwen)

51.1

Rank #36 Confirmed

Reka Flash 3 Reka

36.4

Unranked Sparse

Summary

  • The widest gap is in writing & preference, where Qwen3.6 Max Preview leads 64.0 to 43.8.
  • Reka Flash 3 is cheaper at $0.10 / $0.20 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
  • Qwen3.6 Max Preview accepts more context: 262K tokens versus 66K.
  • Reka Flash 3 has downloadable open weights; the other is API-only.

Side by side

Qwen3.6 Max PreviewReka Flash 3
ProviderAlibaba (Qwen)Reka
Noometry Index51.136.4
Released2026-04-202025-03-10
WeightsProprietaryOpen
Context window262K66K
Max output66K59K
Input $ / M tokens$1.30$0.10
Output $ / M tokens$7.80$0.20
Results tracked292

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

Category by category

Coding Not comparable

Qwen3.6 Max Preview: 48.6 (#50), Reka Flash 3: —

BenchmarkQwen3.6 Max PreviewReka Flash 3
SWE-bench Verified76.7%—
LMArena WebDev1482—
LMArena Coding1472—

Agentic & Tool Use Not comparable

Qwen3.6 Max Preview: —, Reka Flash 3: 30.1

BenchmarkQwen3.6 Max PreviewReka Flash 3
BALROG—29.2%
Vending-Bench 24,254—

Reasoning Not comparable

Qwen3.6 Max Preview: 40.8 (#47), Reka Flash 3: —

BenchmarkQwen3.6 Max PreviewReka Flash 3
SimpleBench63%—
NYT Connections (extended)74.1%—
Chess Puzzles20%—
LMArena Hard Prompts1457—
Mystery Game Puzzles19%—
DTBench87.2%—
LMCA42.5%—
Epoch Capabilities Index149.27—

Math Not comparable

Qwen3.6 Max Preview: 52.2 (#40), Reka Flash 3: —

BenchmarkQwen3.6 Max PreviewReka Flash 3
OTIS Mock AIME 2024-202591.1%—
LMArena Math1465—
FrontierMath (Feb 2025 set)23.1%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Not comparable

Qwen3.6 Max Preview: 57.6 (#35), Reka Flash 3: —

BenchmarkQwen3.6 Max PreviewReka Flash 3
GPQA Diamond87.4%—
SimpleQA Verified52%—
LMArena Expert1476—

Multilingual Not comparable

Qwen3.6 Max Preview: 54.3 (#46), Reka Flash 3: —

BenchmarkQwen3.6 Max PreviewReka Flash 3
LMArena Non-English1436—
LMArena Chinese1487—
LMArena French1449—
LMArena Russian1444—
LMArena Spanish1452—

Instruction Following Not comparable

Qwen3.6 Max Preview: 75.8 (#51), Reka Flash 3: —

BenchmarkQwen3.6 Max PreviewReka Flash 3
LMArena Instruction Following1437—

Long Context Not comparable

Qwen3.6 Max Preview: 44.6 (#59), Reka Flash 3: —

BenchmarkQwen3.6 Max PreviewReka Flash 3
LMArena Longer Query1457—

Writing & Preference Qwen3.6 Max Preview leads

Qwen3.6 Max Preview: 64.0 (#58), Reka Flash 3: 43.8

BenchmarkQwen3.6 Max PreviewReka Flash 3
LMArena Text1447—
LMArena Creative Writing1435—
EQ-Bench Creative Writing—1228
LMArena Multi-Turn1456—

Frequently asked questions

Is Qwen3.6 Max Preview better than Reka Flash 3?

Qwen3.6 Max Preview has enough public results to be ranked (#36); Reka Flash 3 does not yet, so treat this comparison as directional.

Which is cheaper, Qwen3.6 Max Preview 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; Qwen3.6 Max Preview lists at $1.30 and $7.80.

Which has the bigger context window?

Qwen3.6 Max Preview does, with 262K tokens against 66K.

How many benchmarks do Qwen3.6 Max Preview and Reka Flash 3 share?

0 benchmarks have published results for both models. Qwen3.6 Max Preview has 29 scored results on Noometry and Reka Flash 3 has 2.

Related comparisons

Go deeper