Noometry

Model comparison

Gemini 2.5 Flash vs Qwen3.5 397B-A17B

Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 1.6× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.

Last verified . 24 shared benchmarks.

Gemini 2.5 Flash Google

39.3

Rank #170 Confirmed

Qwen3.5 397B-A17B Alibaba (Qwen)

46.0

Rank #67 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 3 categories and Qwen3.5 397B-A17B in 7 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3.5 397B-A17B leads 53.3 to 36.4.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 56.8% for Gemini 2.5 Flash and 73.7% for Qwen3.5 397B-A17B.
  • Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $0.60 / $3.60 for Qwen3.5 397B-A17B.
  • Gemini 2.5 Flash accepts more context: 1.05M tokens versus 262K.
  • Qwen3.5 397B-A17B has downloadable open weights; the other is API-only.

Side by side

Gemini 2.5 FlashQwen3.5 397B-A17B
ProviderGoogleAlibaba (Qwen)
Noometry Index39.346.0
Released2025-04-172026-02-01
WeightsProprietaryOpen
Context window1.05M262K
Max output66K66K
Input $ / M tokens$0.30$0.60
Output $ / M tokens$2.50$3.60
Results tracked5436

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

Category by category

Coding Qwen3.5 397B-A17B leads

Gemini 2.5 Flash: 35.8 (#220), Qwen3.5 397B-A17B: 42.0 (#114)

BenchmarkGemini 2.5 FlashQwen3.5 397B-A17B
LMArena Coding14241465
SWE-bench Verified (bash only)28.7%—
Aider Polyglot55.1%—
LMArena WebDev—1400
WeirdML41.9%—
ALE-Bench661.88—

Agentic & Tool Use Qwen3.5 397B-A17B leads

Gemini 2.5 Flash: 30.8 (#74), Qwen3.5 397B-A17B: 33.3 (#53)

BenchmarkGemini 2.5 FlashQwen3.5 397B-A17B
Terminal-Bench17.1%—
APEX-Agents—24.9%
Berkeley Function Calling Leaderboard56.2%—
TheAgentCompany41.1%—
τ²-bench Airline—81.5%
τ²-bench Banking—9.8%
τ²-bench Retail—84.4%
τ²-bench Telecom—97.8%
BALROG33.5%—
Vending-Bench 2548.84—

Reasoning Qwen3.5 397B-A17B leads

Gemini 2.5 Flash: 18.1 (#286), Qwen3.5 397B-A17B: 34.5 (#70)

BenchmarkGemini 2.5 FlashQwen3.5 397B-A17B
Kagi LLM Benchmark56.8%73.7%
LMArena Hard Prompts14221448
DTBench76.5%87.5%
LMCA27.5%37.9%
Epoch Capabilities Index143.03146.65
ARC-AGI-22.5%—
SimpleBench41.2%—
NYT Connections (extended)—58.9%
ARC-AGI-133.3%—
CritPt1.1%—
Chess Puzzles—13%
EnigmaEval2.7%—
Thematic Generalization—65.1%
Mystery Game Puzzles—18%
ForecastBench60.6—

Math Qwen3.5 397B-A17B leads

Gemini 2.5 Flash: 39.9 (#98), Qwen3.5 397B-A17B: 46.1 (#73)

BenchmarkGemini 2.5 FlashQwen3.5 397B-A17B
OTIS Mock AIME 2024-202573.1%88.9%
LMArena Math14151454
FrontierMath (Tiers 1-3)—31.2%
Omni-MATH38.5%—
FrontierMath (Feb 2025 set)4.8%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Qwen3.5 397B-A17B leads

Gemini 2.5 Flash: 36.4 (#168), Qwen3.5 397B-A17B: 53.3 (#58)

BenchmarkGemini 2.5 FlashQwen3.5 397B-A17B
LMArena Expert14261462
GPQA Diamond—86.4%
Humanity's Last Exam12.1%—
MMLU-Pro63.9%—
Confabulations16.8%—
Vectara Hallucination Rate7.8%—
GPQA (HELM)39%—

Multimodal Gemini 2.5 Flash leads

Gemini 2.5 Flash: 41.8 (#32), Qwen3.5 397B-A17B: 40.7 (#44)

BenchmarkGemini 2.5 FlashQwen3.5 397B-A17B
LMArena Vision12531263
GeoBench76%—
VPCT46.2%—
SpatialViz-Bench36.9%—

Multilingual Qwen3.5 397B-A17B leads

Gemini 2.5 Flash: 52.3 (#88), Qwen3.5 397B-A17B: 53.7 (#59)

BenchmarkGemini 2.5 FlashQwen3.5 397B-A17B
LMArena Non-English14091430
LMArena Chinese14501500
LMArena French14331461
LMArena German14181447
LMArena Japanese14051426
LMArena Korean13851384
LMArena Russian14151429
LMArena Spanish14211441

Instruction Following Too close to call

Gemini 2.5 Flash: 75.7 (#54), Qwen3.5 397B-A17B: 75.0 (#77)

BenchmarkGemini 2.5 FlashQwen3.5 397B-A17B
LMArena Instruction Following14051424
IFEval89.8%—

Long Context Gemini 2.5 Flash leads

Gemini 2.5 Flash: 47.5 (#17), Qwen3.5 397B-A17B: 44.1 (#74)

BenchmarkGemini 2.5 FlashQwen3.5 397B-A17B
LMArena Longer Query14191442
Fiction.LiveBench77.8%—

Writing & Preference Qwen3.5 397B-A17B leads

Gemini 2.5 Flash: 53.8 (#157), Qwen3.5 397B-A17B: 62.3 (#79)

BenchmarkGemini 2.5 FlashQwen3.5 397B-A17B
LMArena Text14171438
LMArena Creative Writing14001401
EQ-Bench Creative Writing11371478
LMArena Multi-Turn14081446
Short-Story Creative Writing76.5%—
WildBench81.7%—

Frequently asked questions

Is Gemini 2.5 Flash better than Qwen3.5 397B-A17B?

Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 1.6× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.

Which is cheaper, Gemini 2.5 Flash or Qwen3.5 397B-A17B?

Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Qwen3.5 397B-A17B lists at $0.60 and $3.60.

Is Gemini 2.5 Flash or Qwen3.5 397B-A17B better for coding?

Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 35.8 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Flash does, with 1.05M tokens against 262K.

How many benchmarks do Gemini 2.5 Flash and Qwen3.5 397B-A17B share?

24 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Qwen3.5 397B-A17B has 36.

Related comparisons

Go deeper