Noometry

Model comparison

Gemini 2.5 Flash vs Qwen3-Next 80B-A3B Instruct

Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 39.3 on the Noometry Index.

Last verified . 25 shared benchmarks.

Gemini 2.5 Flash Google

39.3

Rank #170 Confirmed

Qwen3-Next 80B-A3B Instruct Alibaba (Qwen)

43.0

Rank #102 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 4 categories and Qwen3-Next 80B-A3B Instruct in 4 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Qwen3-Next 80B-A3B Instruct leads 31.1 to 18.1.
  • The biggest single-benchmark swing is GPQA (HELM): 39% for Gemini 2.5 Flash and 63% for Qwen3-Next 80B-A3B Instruct.
  • Both cost about the same: $0.30 input and $2.50 output per million tokens.
  • Gemini 2.5 Flash accepts more context: 1.05M tokens versus 131K.
  • Qwen3-Next 80B-A3B Instruct has downloadable open weights; the other is API-only.

Side by side

Gemini 2.5 FlashQwen3-Next 80B-A3B Instruct
ProviderGoogleAlibaba (Qwen)
Noometry Index39.343.0
Released2025-04-172025-09
WeightsProprietaryOpen
Context window1.05M131K
Max output66K33K
Input $ / M tokens$0.30$0.50
Output $ / M tokens$2.50$2
Results tracked5425

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

Category by category

Coding Qwen3-Next 80B-A3B Instruct leads

Gemini 2.5 Flash: 35.8 (#220), Qwen3-Next 80B-A3B Instruct: 42.5 (#98)

BenchmarkGemini 2.5 FlashQwen3-Next 80B-A3B Instruct
LMArena Coding14241440
SWE-bench Verified (bash only)28.7%—
Aider Polyglot55.1%—
WeirdML41.9%—
ALE-Bench661.88—

Agentic & Tool Use Not comparable

Gemini 2.5 Flash: 30.8 (#74), Qwen3-Next 80B-A3B Instruct: —

BenchmarkGemini 2.5 FlashQwen3-Next 80B-A3B Instruct
Terminal-Bench17.1%—
Berkeley Function Calling Leaderboard56.2%—
TheAgentCompany41.1%—
BALROG33.5%—
Vending-Bench 2548.84—

Reasoning Qwen3-Next 80B-A3B Instruct leads

Gemini 2.5 Flash: 18.1 (#286), Qwen3-Next 80B-A3B Instruct: 31.1 (#81)

BenchmarkGemini 2.5 FlashQwen3-Next 80B-A3B Instruct
Kagi LLM Benchmark56.8%66.7%
LMArena Hard Prompts14221428
ARC-AGI-22.5%—
SimpleBench41.2%—
ARC-AGI-133.3%—
CritPt1.1%—
EnigmaEval2.7%—
DTBench76.5%—
LMCA27.5%—
Epoch Capabilities Index143.03—
ForecastBench60.6—

Math Gemini 2.5 Flash leads

Gemini 2.5 Flash: 39.9 (#98), Qwen3-Next 80B-A3B Instruct: 38.8 (#126)

BenchmarkGemini 2.5 FlashQwen3-Next 80B-A3B Instruct
Omni-MATH38.5%46.7%
LMArena Math14151440
OTIS Mock AIME 2024-202573.1%—
FrontierMath (Feb 2025 set)4.8%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Qwen3-Next 80B-A3B Instruct leads

Gemini 2.5 Flash: 36.4 (#168), Qwen3-Next 80B-A3B Instruct: 41.8 (#106)

BenchmarkGemini 2.5 FlashQwen3-Next 80B-A3B Instruct
MMLU-Pro63.9%78.6%
Vectara Hallucination Rate7.8%9.3%
GPQA (HELM)39%63%
LMArena Expert14261417
Humanity's Last Exam12.1%—
Confabulations16.8%—

Multimodal Not comparable

Gemini 2.5 Flash: 41.8 (#32), Qwen3-Next 80B-A3B Instruct: —

BenchmarkGemini 2.5 FlashQwen3-Next 80B-A3B Instruct
LMArena Vision1253—
GeoBench76%—
VPCT46.2%—
SpatialViz-Bench36.9%—

Multilingual Too close to call

Gemini 2.5 Flash: 52.3 (#88), Qwen3-Next 80B-A3B Instruct: 52.1 (#93)

BenchmarkGemini 2.5 FlashQwen3-Next 80B-A3B Instruct
LMArena Non-English14091407
LMArena Chinese14501460
LMArena French14331413
LMArena German14181417
LMArena Japanese14051395
LMArena Korean13851364
LMArena Russian14151404
LMArena Spanish14211435

Instruction Following Gemini 2.5 Flash leads

Gemini 2.5 Flash: 75.7 (#54), Qwen3-Next 80B-A3B Instruct: 70.8 (#159)

BenchmarkGemini 2.5 FlashQwen3-Next 80B-A3B Instruct
IFEval89.8%81%
LMArena Instruction Following14051389

Long Context Gemini 2.5 Flash leads

Gemini 2.5 Flash: 47.5 (#17), Qwen3-Next 80B-A3B Instruct: 37.0 (#223)

BenchmarkGemini 2.5 FlashQwen3-Next 80B-A3B Instruct
Fiction.LiveBench77.8%55.6%
LMArena Longer Query14191403

Writing & Preference Qwen3-Next 80B-A3B Instruct leads

Gemini 2.5 Flash: 53.8 (#157), Qwen3-Next 80B-A3B Instruct: 58.0 (#121)

BenchmarkGemini 2.5 FlashQwen3-Next 80B-A3B Instruct
LMArena Text14171417
LMArena Creative Writing14001334
WildBench81.7%80.7%
LMArena Multi-Turn14081416
Short-Story Creative Writing76.5%—
EQ-Bench Creative Writing1137—

Frequently asked questions

Is Gemini 2.5 Flash better than Qwen3-Next 80B-A3B Instruct?

Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 39.3 on the Noometry Index.

Which is cheaper, Gemini 2.5 Flash or Qwen3-Next 80B-A3B Instruct?

Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Qwen3-Next 80B-A3B Instruct lists at $0.50 and $2.

Is Gemini 2.5 Flash or Qwen3-Next 80B-A3B Instruct better for coding?

Qwen3-Next 80B-A3B Instruct scores higher on coding benchmarks: 42.5 versus 35.8 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Flash does, with 1.05M tokens against 131K.

How many benchmarks do Gemini 2.5 Flash and Qwen3-Next 80B-A3B Instruct share?

25 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Qwen3-Next 80B-A3B Instruct has 25.

Related comparisons

Go deeper