Model comparison

Gemini 3 Flash Preview vs Qwen3-4B

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 31.9 on the Noometry Index.

Last verified . 5 shared benchmarks.

Gemini 3 Flash Preview Google

52.3

Rank #40 Confirmed

Qwen3-4B Alibaba (Qwen)

31.9

Rank #264 Confirmed

Summary

  • They share 5 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 4 categories and Qwen3-4B in 0 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 19.2.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Gemini 3 Flash Preview and 52.2% for Qwen3-4B.
  • Qwen3-4B has downloadable open weights; the other is API-only.

Side by side

Gemini 3 Flash Preview and Qwen3-4B specifications
Gemini 3 Flash PreviewQwen3-4B
ProviderGoogleAlibaba (Qwen)
Noometry Index52.331.9
Released2025-12-172025-04-29
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$0.50—
Output $ / M tokens$3—
Results tracked596

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

Category by category

Coding Not comparable

Gemini 3 Flash Preview: 50.9 (#42), Qwen3-4B: —

Coding benchmarks
BenchmarkGemini 3 Flash PreviewQwen3-4B
SWE-bench Verified75.4%—
SWE-bench Verified (bash only)75.8%—
LMArena WebDev1439—
SWE-bench Multilingual72.7%—
GSO9.8%—
WeirdML61.6%—
LMArena Coding1460—
ALE-Bench1,367—

Agentic & Tool Use Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 38.7 (#29), Qwen3-4B: 27.6 (#100)

Agentic & Tool Use benchmarks
BenchmarkGemini 3 Flash PreviewQwen3-4B
Terminal-Bench64.3%—
Berkeley Function Calling Leaderboard—35.7%
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—
Vending-Bench 23,635—

Reasoning Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 49.2 (#37), Qwen3-4B: 19.2 (#268)

Reasoning benchmarks
BenchmarkGemini 3 Flash PreviewQwen3-4B
Chess Puzzles40%4%
ARC-AGI-233.6%—
SimpleBench61.1%—
NYT Connections (extended)83.1%—
ARC-AGI-184.7%—
LMArena Hard Prompts1465—
Mystery Game Puzzles26%—
DTBench89.1%—
LMCA43.1%—
Epoch Capabilities Index151.8—
ForecastBench58.5—

Math Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 51.7 (#55), Qwen3-4B: 29.7 (#240)

Math benchmarks
BenchmarkGemini 3 Flash PreviewQwen3-4B
MathArena Final-Answer Competitions67.6%38.5%
OTIS Mock AIME 2024-202595.6%52.2%
FrontierMath (Tiers 1-3)51.2%—
FrontierMath Tier 417.1%—
ProofBench15%—
LMArena Math1473—
FrontierMath (Feb 2025 set)35.6%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 58.8 (#33), Qwen3-4B: 33.0 (#208)

Knowledge benchmarks
BenchmarkGemini 3 Flash PreviewQwen3-4B
GPQA Diamond89.4%52.3%
Vectara Hallucination Rate13.5%5.7%
SimpleQA Verified66.8%—
LMArena Expert1462—

Multimodal Not comparable

Gemini 3 Flash Preview: 45.5 (#16), Qwen3-4B: —

Multimodal benchmarks
BenchmarkGemini 3 Flash PreviewQwen3-4B
LMArena Vision1285—
GeoBench88%—
VPCT72.6%—
Blueprint-Bench 20%—
LMArena Document1413—

Multilingual Not comparable

Gemini 3 Flash Preview: 55.7 (#27), Qwen3-4B: —

Multilingual benchmarks
BenchmarkGemini 3 Flash PreviewQwen3-4B
LMArena Non-English1458—
LMArena Chinese1511—
LMArena French1477—
LMArena German1497—
LMArena Japanese1489—
LMArena Korean1443—
LMArena Russian1480—
LMArena Spanish1469—

Instruction Following Not comparable

Gemini 3 Flash Preview: 75.7 (#56), Qwen3-4B: —

Instruction Following benchmarks
BenchmarkGemini 3 Flash PreviewQwen3-4B
LMArena Instruction Following1437—

Long Context Not comparable

Gemini 3 Flash Preview: 44.4 (#67), Qwen3-4B: —

Long Context benchmarks
BenchmarkGemini 3 Flash PreviewQwen3-4B
LMArena Longer Query1452—

Writing & Preference Not comparable

Gemini 3 Flash Preview: 65.5 (#45), Qwen3-4B: —

Writing & Preference benchmarks
BenchmarkGemini 3 Flash PreviewQwen3-4B
LMArena Text1466—
LMArena Creative Writing1457—
LMArena Multi-Turn1471—

Frequently asked questions

Is Gemini 3 Flash Preview better than Qwen3-4B?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 31.9 on the Noometry Index.

How many benchmarks do Gemini 3 Flash Preview and Qwen3-4B share?

5 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and Qwen3-4B has 6.

Related comparisons

Go deeper