Noometry

Model comparison

Gemini 3.1 Flash Lite vs Qwen2-72B

Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.8 to 30.0 on the Noometry Index.

Last verified . 20 shared benchmarks.

Gemini 3.1 Flash Lite Google

40.8

Rank #144 Confirmed

Qwen2-72B Alibaba (Qwen)

30.0

Rank #300 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 8 categories and Qwen2-72B in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Gemini 3.1 Flash Lite leads 41.9 to 21.2.
  • The biggest single-benchmark swing is GPQA Diamond: 81.8% for Gemini 3.1 Flash Lite and 40.8% for Qwen2-72B.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

Gemini 3.1 Flash LiteQwen2-72B
ProviderGoogleAlibaba (Qwen)
Noometry Index40.830.0
Released2026-03-032024-06-07
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$0.25—
Output $ / M tokens$1.50—
Results tracked3826

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

Category by category

Coding Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 37.8 (#188), Qwen2-72B: 29.1 (#310)

BenchmarkGemini 3.1 Flash LiteQwen2-72B
WeirdML52.2%11.3%
LMArena Coding14001196
LMArena WebDev1256—
SciCode41.9%—
BigCodeBench Instruct—38.5%
BigCodeBench Complete—54%
ALE-Bench797.73—

Agentic & Tool Use Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 30.2 (#79), Qwen2-72B: 17.0 (#146)

BenchmarkGemini 3.1 Flash LiteQwen2-72B
TheAgentCompany—1.1%
DeepResearch Bench37.3%—
METR Time Horizons—29.9%

Reasoning Too close to call

Gemini 3.1 Flash Lite: 22.9 (#186), Qwen2-72B: 23.2 (#181)

BenchmarkGemini 3.1 Flash LiteQwen2-72B
LMArena Hard Prompts14071191
Epoch Capabilities Index144.47125.28
Kagi LLM Benchmark67.2%—
NYT Connections (extended)8.2%—
CritPt1.1%—
Chess Puzzles25%—
EnigmaEval3%—
Thematic Generalization63.3%—
DTBench76.8%—
LMCA35%—
ForecastBench54.4—

Math Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 40.7 (#90), Qwen2-72B: 30.2 (#236)

BenchmarkGemini 3.1 Flash LiteQwen2-72B
LMArena Math14281235
FrontierMath (Tiers 1-3)27.7%—
OTIS Mock AIME 2024-202580%—
MATH Level 5—39.1%

Knowledge Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 41.9 (#104), Qwen2-72B: 21.2 (#275)

BenchmarkGemini 3.1 Flash LiteQwen2-72B
GPQA Diamond81.8%40.8%
LMArena Expert13981171
Humanity's Last Exam8.6%—
Vectara Hallucination Rate8.2%—
MMLU—82.4%

Multimodal Not comparable

Gemini 3.1 Flash Lite: 39.4 (#60), Qwen2-72B: —

BenchmarkGemini 3.1 Flash LiteQwen2-72B
LMArena Vision1240—

Multilingual Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 52.3 (#86), Qwen2-72B: 35.9 (#244)

BenchmarkGemini 3.1 Flash LiteQwen2-72B
LMArena Non-English14111176
LMArena Chinese14611240
LMArena French14241170
LMArena German14291151
LMArena Japanese14131111
LMArena Korean13921083
LMArena Russian14201169
LMArena Spanish14211169

Instruction Following Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 72.7 (#131), Qwen2-72B: 61.7 (#241)

BenchmarkGemini 3.1 Flash LiteQwen2-72B
LMArena Instruction Following13771181

Long Context Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 42.5 (#122), Qwen2-72B: 36.1 (#235)

BenchmarkGemini 3.1 Flash LiteQwen2-72B
LMArena Longer Query13941192

Writing & Preference Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 60.9 (#94), Qwen2-72B: 40.8 (#241)

BenchmarkGemini 3.1 Flash LiteQwen2-72B
LMArena Text14161203
LMArena Creative Writing14011181
LMArena Multi-Turn14171196

Frequently asked questions

Is Gemini 3.1 Flash Lite better than Qwen2-72B?

Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.8 to 30.0 on the Noometry Index.

Is Gemini 3.1 Flash Lite or Qwen2-72B better for coding?

Gemini 3.1 Flash Lite scores higher on coding benchmarks: 37.8 versus 29.1 in the Noometry coding category.

How many benchmarks do Gemini 3.1 Flash Lite and Qwen2-72B share?

20 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and Qwen2-72B has 26.

Related comparisons

Go deeper