Noometry

Model comparison

Gemini 3 Flash Preview vs Qwen3 235B-A22B

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 43.2 on the Noometry Index.

Last verified . 34 shared benchmarks.

Gemini 3 Flash Preview Google

52.3

Rank #33 Confirmed

Qwen3 235B-A22B Alibaba (Qwen)

43.2

Rank #83 Confirmed

Summary

  • They share 34 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 8 categories and Qwen3 235B-A22B in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 15.8.
  • The biggest single-benchmark swing is ARC-AGI-1: 84.7% for Gemini 3 Flash Preview and 11% for Qwen3 235B-A22B.
  • Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $0.70 / $2.80 for Qwen3 235B-A22B.
  • Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 131K.
  • Qwen3 235B-A22B has downloadable open weights; the other is API-only.

Side by side

Gemini 3 Flash PreviewQwen3 235B-A22B
ProviderGoogleAlibaba (Qwen)
Noometry Index52.343.2
Released2025-12-172025-04
WeightsProprietaryOpen
Context window1.05M131K
Max output66K16K
Input $ / M tokens$0.50$0.70
Output $ / M tokens$3$2.80
Results tracked5949

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

Category by category

Coding Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 51.5 (#35), Qwen3 235B-A22B: 43.8 (#72)

BenchmarkGemini 3 Flash PreviewQwen3 235B-A22B
WeirdML61.6%41%
LMArena Coding14601445
SWE-bench Verified75.4%—
SWE-bench Verified (bash only)75.8%—
Aider Polyglot—59.6%
LMArena WebDev1439—
SWE-bench Multilingual72.7%—
SciCode—42.4%
GSO9.8%—
ALE-Bench1,367—

Agentic & Tool Use Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 38.6 (#27), Qwen3 235B-A22B: 33.7 (#48)

BenchmarkGemini 3 Flash PreviewQwen3 235B-A22B
Vending-Bench 23,635-11.34
Terminal-Bench64.3%—
Berkeley Function Calling Leaderboard—52.1%
τ²-bench Airline82.5%—
τ²-bench Banking27.3%—
τ²-bench Retail76.8%—
τ²-bench Telecom91.2%—
DeepResearch Bench49.8%—
BALROG48.1%—
GDP.pdf10%—
LMArena Search1198—

Reasoning Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 49.2 (#35), Qwen3 235B-A22B: 15.8 (#302)

BenchmarkGemini 3 Flash PreviewQwen3 235B-A22B
ARC-AGI-233.6%1.3%
SimpleBench61.1%31%
ARC-AGI-184.7%11%
Chess Puzzles40%12%
LMArena Hard Prompts14651433
Mystery Game Puzzles26%9%
DTBench89.1%80.3%
LMCA43.1%29.3%
Epoch Capabilities Index151.83143.87
ForecastBench58.559.7
Kagi LLM Benchmark—69.4%
NYT Connections (extended)83.1%—
CritPt—0%

Math Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 51.4 (#42), Qwen3 235B-A22B: 48.5 (#51)

BenchmarkGemini 3 Flash PreviewQwen3 235B-A22B
OTIS Mock AIME 2024-202595.6%86.7%
LMArena Math14721431
FrontierMath (Feb 2025 set)35.6%8.5%
FrontierMath Tier 4 (v1)4.2%0%
FrontierMath (Tiers 1-3)51.2%—
FrontierMath Tier 417.1%—
MathArena Final-Answer Competitions67.6%—
ProofBench15%—
Omni-MATH—71.8%
MATH Level 5—68.9%

Knowledge Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 58.8 (#30), Qwen3 235B-A22B: 49.5 (#67)

BenchmarkGemini 3 Flash PreviewQwen3 235B-A22B
GPQA Diamond89.4%80.1%
SimpleQA Verified66.8%40.4%
Vectara Hallucination Rate13.5%9.3%
LMArena Expert14611460
MMLU-Pro—84.4%
Confabulations—15.6%
GPQA (HELM)—72.7%

Multimodal Not comparable

Gemini 3 Flash Preview: 45.3 (#15), Qwen3 235B-A22B: —

BenchmarkGemini 3 Flash PreviewQwen3 235B-A22B
LMArena Vision1285—
GeoBench88%—
VPCT72.6%—
Blueprint-Bench 20%—
LMArena Document1413—

Multilingual Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 55.9 (#26), Qwen3 235B-A22B: 52.5 (#84)

BenchmarkGemini 3 Flash PreviewQwen3 235B-A22B
LMArena Non-English14581410
LMArena Chinese15101481
LMArena French14781445
LMArena German14971432
LMArena Japanese14881400
LMArena Korean14431391
LMArena Russian14801411
LMArena Spanish14701429

Instruction Following Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 75.8 (#52), Qwen3 235B-A22B: 72.8 (#132)

BenchmarkGemini 3 Flash PreviewQwen3 235B-A22B
LMArena Instruction Following14371408
IFEval—83.5%

Long Context Qwen3 235B-A22B leads

Gemini 3 Flash Preview: 44.4 (#63), Qwen3 235B-A22B: 46.1 (#25)

BenchmarkGemini 3 Flash PreviewQwen3 235B-A22B
LMArena Longer Query14521426
Fiction.LiveBench—75%

Writing & Preference Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 65.6 (#44), Qwen3 235B-A22B: 59.8 (#103)

BenchmarkGemini 3 Flash PreviewQwen3 235B-A22B
LMArena Text14661419
LMArena Creative Writing14571384
LMArena Multi-Turn14711432
Short-Story Creative Writing—83%
EQ-Bench Creative Writing—1366
WildBench—86.6%

Frequently asked questions

Is Gemini 3 Flash Preview better than Qwen3 235B-A22B?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 43.2 on the Noometry Index.

Which is cheaper, Gemini 3 Flash Preview or Qwen3 235B-A22B?

Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; Qwen3 235B-A22B lists at $0.70 and $2.80.

Is Gemini 3 Flash Preview or Qwen3 235B-A22B better for coding?

Gemini 3 Flash Preview scores higher on coding benchmarks: 51.5 versus 43.8 in the Noometry coding category.

Which has the bigger context window?

Gemini 3 Flash Preview does, with 1.05M tokens against 131K.

How many benchmarks do Gemini 3 Flash Preview and Qwen3 235B-A22B share?

34 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and Qwen3 235B-A22B has 49.

Related comparisons

Go deeper