Noometry

Model comparison

Gemini 3.1 Pro Preview vs Qwen3 235B-A22B

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 43.5 on the Noometry Index. Qwen3 235B-A22B costs 3.7× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Last verified . 37 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

Qwen3 235B-A22B Alibaba (Qwen)

43.5

Rank #91 Confirmed

Summary

  • They share 37 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 8 categories and Qwen3 235B-A22B in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 15.7.
  • The biggest single-benchmark swing is ARC-AGI-1: 98% for Gemini 3.1 Pro Preview and 11% for Qwen3 235B-A22B.
  • Qwen3 235B-A22B is cheaper at $0.70 / $2.80 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
  • Gemini 3.1 Pro Preview 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 Pro PreviewQwen3 235B-A22B
ProviderGoogleAlibaba (Qwen)
Noometry Index56.743.5
Released2026-02-192025-04
WeightsProprietaryOpen
Context window1.05M131K
Max output66K16K
Input $ / M tokens$2$0.70
Output $ / M tokens$12$2.80
Results tracked7149

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

Category by category

Coding Qwen3 235B-A22B leads

Gemini 3.1 Pro Preview: 42.5 (#99), Qwen3 235B-A22B: 44.3 (#75)

BenchmarkGemini 3.1 Pro PreviewQwen3 235B-A22B
SciCode58.9%42.4%
WeirdML72.1%41%
LMArena Coding14841445
SWE-bench Verified75.6%—
DeepSWE11.7%—
Aider Polyglot—59.6%
LMArena WebDev1447—
GSO22.6%—
MirrorCode8.9%—
ALE-Bench1,161—
AlgoTune2.02—

Agentic & Tool Use Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 37.7 (#34), Qwen3 235B-A22B: 33.9 (#51)

BenchmarkGemini 3.1 Pro PreviewQwen3 235B-A22B
Vending-Bench 23,774-11.34
Terminal-Bench80.2%—
APEX-Agents35.3%—
Berkeley Function Calling Leaderboard—52.1%
τ²-bench Banking26%—
DeepResearch Bench47.8%—
PostTrainBench22%—
BALROG57%—
ExploitBench26.1%—
GBAEval0.8%—
GDP.pdf17%—
LMArena Search1211—
METR Time Horizons77%—

Reasoning Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.7 (#12), Qwen3 235B-A22B: 15.7 (#311)

BenchmarkGemini 3.1 Pro PreviewQwen3 235B-A22B
ARC-AGI-277.1%1.3%
SimpleBench79.6%31%
ARC-AGI-198%11%
CritPt17.7%0%
Chess Puzzles55%12%
LMArena Hard Prompts14851433
Mystery Game Puzzles34%9%
DTBench97.1%80.3%
LMCA53.8%29.3%
Epoch Capabilities Index154.77143.85
ForecastBench5959.7
Kagi LLM Benchmark—69.4%
NYT Connections (extended)97.4%—
EnigmaEval36.8%—
Thematic Generalization79.4%—
EBR-Bench14.3%—

Math Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 62.1 (#34), Qwen3 235B-A22B: 50.4 (#57)

BenchmarkGemini 3.1 Pro PreviewQwen3 235B-A22B
OTIS Mock AIME 2024-202595.6%86.7%
LMArena Math14851432
FrontierMath (Feb 2025 set)36.9%8.5%
FrontierMath Tier 4 (v1)16.7%0%
FrontierMath (Tiers 1-3)59.6%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions86.5%—
ProofBench26%—
Omni-MATH—71.8%
MATH Level 5—68.9%

Knowledge Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.8 (#3), Qwen3 235B-A22B: 49.6 (#73)

BenchmarkGemini 3.1 Pro PreviewQwen3 235B-A22B
GPQA Diamond94.4%80.1%
SimpleQA Verified73.5%40.4%
Vectara Hallucination Rate10.4%9.3%
LMArena Expert14851463
Humanity's Last Exam46.4%—
MMLU-Pro—84.4%
Confabulations—15.6%
GPQA (HELM)—72.7%

Multimodal Not comparable

Gemini 3.1 Pro Preview: 37.9 (#69), Qwen3 235B-A22B: —

BenchmarkGemini 3.1 Pro PreviewQwen3 235B-A22B
LMArena Vision1296—
Blueprint-Bench 226.5%—
Furniture Assembly26.7%—
LMArena Document1444—

Multilingual Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 57.0 (#12), Qwen3 235B-A22B: 52.3 (#89)

BenchmarkGemini 3.1 Pro PreviewQwen3 235B-A22B
LMArena Non-English14771409
LMArena Chinese15291481
LMArena French14871445
LMArena German14911433
LMArena Japanese14931399
LMArena Korean14551391
LMArena Russian14981411
LMArena Spanish14791430

Instruction Following Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 77.0 (#32), Qwen3 235B-A22B: 72.6 (#136)

BenchmarkGemini 3.1 Pro PreviewQwen3 235B-A22B
LMArena Instruction Following14661408
IFEval—83.5%

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.4 (#18), Qwen3 235B-A22B: 46.1 (#26)

BenchmarkGemini 3.1 Pro PreviewQwen3 235B-A22B
LMArena Longer Query14831426
Fiction.LiveBench—75%
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 66.1 (#37), Qwen3 235B-A22B: 59.6 (#108)

BenchmarkGemini 3.1 Pro PreviewQwen3 235B-A22B
LMArena Text14811419
LMArena Creative Writing14821384
EQ-Bench Creative Writing14911366
LMArena Multi-Turn14881432
Short-Story Creative Writing—83%
WildBench—86.6%
EQ-Bench 41142—

Frequently asked questions

Is Gemini 3.1 Pro Preview better than Qwen3 235B-A22B?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 43.5 on the Noometry Index. Qwen3 235B-A22B costs 3.7× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Which is cheaper, Gemini 3.1 Pro Preview or Qwen3 235B-A22B?

Qwen3 235B-A22B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or Qwen3 235B-A22B better for coding?

Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 42.5 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 131K.

How many benchmarks do Gemini 3.1 Pro Preview and Qwen3 235B-A22B share?

37 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Qwen3 235B-A22B has 49.

Related comparisons

Go deeper