Noometry

Model comparison

Gemini 3.1 Flash Lite vs Qwen3 235B-A22B

Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 2.2× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.

Last verified . 29 shared benchmarks.

Gemini 3.1 Flash Lite Google

40.8

Rank #144 Confirmed

Qwen3 235B-A22B Alibaba (Qwen)

43.5

Rank #91 Confirmed

Summary

  • They share 29 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 4 categories and Qwen3 235B-A22B in 5 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3 235B-A22B leads 50.4 to 40.7.
  • The biggest single-benchmark swing is Chess Puzzles: 25% for Gemini 3.1 Flash Lite and 12% for Qwen3 235B-A22B.
  • Gemini 3.1 Flash Lite is cheaper at $0.25 / $1.50 per million input/output tokens, against $0.70 / $2.80 for Qwen3 235B-A22B.
  • Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 131K.
  • Qwen3 235B-A22B has downloadable open weights; the other is API-only.

Side by side

Gemini 3.1 Flash LiteQwen3 235B-A22B
ProviderGoogleAlibaba (Qwen)
Noometry Index40.843.5
Released2026-03-032025-04
WeightsProprietaryOpen
Context window1.05M131K
Max output66K16K
Input $ / M tokens$0.25$0.70
Output $ / M tokens$1.50$2.80
Results tracked3849

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

Category by category

Coding Qwen3 235B-A22B leads

Gemini 3.1 Flash Lite: 37.8 (#188), Qwen3 235B-A22B: 44.3 (#75)

BenchmarkGemini 3.1 Flash LiteQwen3 235B-A22B
SciCode41.9%42.4%
WeirdML52.2%41%
LMArena Coding14001445
Aider Polyglot—59.6%
LMArena WebDev1256—
ALE-Bench797.73—

Agentic & Tool Use Qwen3 235B-A22B leads

Gemini 3.1 Flash Lite: 30.2 (#79), Qwen3 235B-A22B: 33.9 (#51)

BenchmarkGemini 3.1 Flash LiteQwen3 235B-A22B
Berkeley Function Calling Leaderboard—52.1%
DeepResearch Bench37.3%—
Vending-Bench 2—-11.34

Reasoning Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 22.9 (#186), Qwen3 235B-A22B: 15.7 (#311)

BenchmarkGemini 3.1 Flash LiteQwen3 235B-A22B
Kagi LLM Benchmark67.2%69.4%
CritPt1.1%0%
Chess Puzzles25%12%
LMArena Hard Prompts14071433
DTBench76.8%80.3%
LMCA35%29.3%
Epoch Capabilities Index144.47143.85
ForecastBench54.459.7
ARC-AGI-2—1.3%
SimpleBench—31%
NYT Connections (extended)8.2%—
ARC-AGI-1—11%
EnigmaEval3%—
Thematic Generalization63.3%—
Mystery Game Puzzles—9%

Math Qwen3 235B-A22B leads

Gemini 3.1 Flash Lite: 40.7 (#90), Qwen3 235B-A22B: 50.4 (#57)

BenchmarkGemini 3.1 Flash LiteQwen3 235B-A22B
OTIS Mock AIME 2024-202580%86.7%
LMArena Math14281432
FrontierMath (Tiers 1-3)27.7%—
Omni-MATH—71.8%
MATH Level 5—68.9%
FrontierMath (Feb 2025 set)—8.5%
FrontierMath Tier 4 (v1)—0%

Knowledge Qwen3 235B-A22B leads

Gemini 3.1 Flash Lite: 41.9 (#104), Qwen3 235B-A22B: 49.6 (#73)

BenchmarkGemini 3.1 Flash LiteQwen3 235B-A22B
GPQA Diamond81.8%80.1%
Vectara Hallucination Rate8.2%9.3%
LMArena Expert13981463
Humanity's Last Exam8.6%—
SimpleQA Verified—40.4%
MMLU-Pro—84.4%
Confabulations—15.6%
GPQA (HELM)—72.7%

Multimodal Not comparable

Gemini 3.1 Flash Lite: 39.4 (#60), Qwen3 235B-A22B: —

BenchmarkGemini 3.1 Flash LiteQwen3 235B-A22B
LMArena Vision1240—

Multilingual Too close to call

Gemini 3.1 Flash Lite: 52.3 (#86), Qwen3 235B-A22B: 52.3 (#89)

BenchmarkGemini 3.1 Flash LiteQwen3 235B-A22B
LMArena Non-English14111409
LMArena Chinese14611481
LMArena French14241445
LMArena German14291433
LMArena Japanese14131399
LMArena Korean13921391
LMArena Russian14201411
LMArena Spanish14211430

Instruction Following Too close to call

Gemini 3.1 Flash Lite: 72.7 (#131), Qwen3 235B-A22B: 72.6 (#136)

BenchmarkGemini 3.1 Flash LiteQwen3 235B-A22B
LMArena Instruction Following13771408
IFEval—83.5%

Long Context Qwen3 235B-A22B leads

Gemini 3.1 Flash Lite: 42.5 (#122), Qwen3 235B-A22B: 46.1 (#26)

BenchmarkGemini 3.1 Flash LiteQwen3 235B-A22B
LMArena Longer Query13941426
Fiction.LiveBench—75%

Writing & Preference Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 60.9 (#94), Qwen3 235B-A22B: 59.6 (#108)

BenchmarkGemini 3.1 Flash LiteQwen3 235B-A22B
LMArena Text14161419
LMArena Creative Writing14011384
LMArena Multi-Turn14171432
Short-Story Creative Writing—83%
EQ-Bench Creative Writing—1366
WildBench—86.6%

Frequently asked questions

Is Gemini 3.1 Flash Lite better than Qwen3 235B-A22B?

Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 2.2× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.

Which is cheaper, Gemini 3.1 Flash Lite or Qwen3 235B-A22B?

Gemini 3.1 Flash Lite is cheaper. It lists at $0.25 per million input tokens and $1.50 per million output tokens; Qwen3 235B-A22B lists at $0.70 and $2.80.

Is Gemini 3.1 Flash Lite or Qwen3 235B-A22B better for coding?

Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 37.8 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Flash Lite does, with 1.05M tokens against 131K.

How many benchmarks do Gemini 3.1 Flash Lite and Qwen3 235B-A22B share?

29 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and Qwen3 235B-A22B has 49.

Related comparisons

Go deeper