Noometry

Model comparison

Gemini 3.8 Flash vs Qwen1.5-72B

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 30.8 on the Noometry Index.

Last verified . 18 shared benchmarks.

Gemini 3.8 Flash Google

61.8

Rank #11 Confirmed

Qwen1.5-72B Alibaba (Qwen)

30.8

Rank #285 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 8 categories and Qwen1.5-72B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Gemini 3.8 Flash leads 74.8 to 11.5.
  • The biggest single-benchmark swing is GPQA Diamond: 95.4% for Gemini 3.8 Flash and 28.8% for Qwen1.5-72B.
  • Qwen1.5-72B has downloadable open weights; the other is API-only.

Side by side

Gemini 3.8 FlashQwen1.5-72B
ProviderGoogleAlibaba (Qwen)
Noometry Index61.830.8
Released2026-09-022024-02-04
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$0.75—
Output $ / M tokens$3.75—
Results tracked5022

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

Category by category

Coding Gemini 3.8 Flash leads

Gemini 3.8 Flash: 59.2 (#15), Qwen1.5-72B: 31.9 (#277)

BenchmarkGemini 3.8 FlashQwen1.5-72B
LMArena Coding15101165
DeepSWE73.8%—
FrontierCode41.2%—
CursorBench39.6%—
LMArena WebDev1584—
FrontierSWE19.6%—
SciCode56.6%—
WeirdML84.8%—
BigCodeBench Instruct—33.2%
BigCodeBench Complete—40.3%
ALE-Bench1,270—
HumanEval+—59.1%
MBPP+—61.6%

Agentic & Tool Use Not comparable

Gemini 3.8 Flash: 41.8 (#21), Qwen1.5-72B: —

BenchmarkGemini 3.8 FlashQwen1.5-72B
APEX-Agents64.3%—
Remote Labor Index5.8%—
GDP.pdf23.4%—
Vending-Bench 25,094—

Reasoning Gemini 3.8 Flash leads

Gemini 3.8 Flash: 76.9 (#5), Qwen1.5-72B: 22.2 (#203)

BenchmarkGemini 3.8 FlashQwen1.5-72B
LMArena Hard Prompts15081148
ARC-AGI-289.2%—
NYT Connections (extended)97.4%—
ARC-AGI-198.5%—
CritPt18.3%—
Chess Puzzles61%—
Mystery Game Puzzles47%—
DTBench95.7%—
LMCA52.9%—
Surface Evolver Bench76.9%—
Epoch Capabilities Index156.71—

Math Gemini 3.8 Flash leads

Gemini 3.8 Flash: 65.3 (#28), Qwen1.5-72B: 33.2 (#205)

BenchmarkGemini 3.8 FlashQwen1.5-72B
LMArena Math15281164
FrontierMath (Tiers 1-3)68.4%—
FrontierMath Tier 422%—
OTIS Mock AIME 2024-202598.9%—
ProofBench48%—

Knowledge Gemini 3.8 Flash leads

Gemini 3.8 Flash: 74.8 (#2), Qwen1.5-72B: 11.5 (#300)

BenchmarkGemini 3.8 FlashQwen1.5-72B
GPQA Diamond95.4%28.8%
LMArena Expert15241136
Humanity's Last Exam44.5%—
SimpleQA Verified69.7%—

Multimodal Not comparable

Gemini 3.8 Flash: 40.7 (#45), Qwen1.5-72B: —

BenchmarkGemini 3.8 FlashQwen1.5-72B
LMArena Vision1314—
Blueprint-Bench 238.6%—
Furniture Assembly31.7%—

Multilingual Gemini 3.8 Flash leads

Gemini 3.8 Flash: 58.0 (#5), Qwen1.5-72B: 33.2 (#253)

BenchmarkGemini 3.8 FlashQwen1.5-72B
LMArena Non-English14911135
LMArena Chinese15541186
LMArena French14981159
LMArena German14931084
LMArena Japanese15021061
LMArena Korean14591050
LMArena Russian15151104
LMArena Spanish14851110

Instruction Following Gemini 3.8 Flash leads

Gemini 3.8 Flash: 78.0 (#13), Qwen1.5-72B: 59.3 (#256)

BenchmarkGemini 3.8 FlashQwen1.5-72B
LMArena Instruction Following14901141

Long Context Gemini 3.8 Flash leads

Gemini 3.8 Flash: 46.3 (#24), Qwen1.5-72B: 35.1 (#243)

BenchmarkGemini 3.8 FlashQwen1.5-72B
LMArena Longer Query15081157

Writing & Preference Gemini 3.8 Flash leads

Gemini 3.8 Flash: 72.2 (#15), Qwen1.5-72B: 37.3 (#258)

BenchmarkGemini 3.8 FlashQwen1.5-72B
LMArena Text14991166
LMArena Creative Writing14921137
LMArena Multi-Turn15011160
EQ-Bench Creative Writing1748—

Frequently asked questions

Is Gemini 3.8 Flash better than Qwen1.5-72B?

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 30.8 on the Noometry Index.

Is Gemini 3.8 Flash or Qwen1.5-72B better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 31.9 in the Noometry coding category.

How many benchmarks do Gemini 3.8 Flash and Qwen1.5-72B share?

18 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and Qwen1.5-72B has 22.

Related comparisons

Go deeper