Noometry

Model comparison

GPT-4o mini vs Qwen3-Coder 480B-A35B Instruct

Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 38.1 to 25.5 on the Noometry Index. GPT-4o mini costs 11× less per token, which makes it the better buy when Qwen3-Coder 480B-A35B Instruct's lead doesn't matter for your workload.

Last verified . 19 shared benchmarks.

GPT-4o mini OpenAI

25.5

Rank #343 Confirmed

Qwen3-Coder 480B-A35B Instruct Alibaba (Qwen)

38.1

Rank #190 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GPT-4o mini scores higher in 1 category and Qwen3-Coder 480B-A35B Instruct in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3-Coder 480B-A35B Instruct leads 37.6 to 10.4.
  • The biggest single-benchmark swing is WeirdML: 11.8% for GPT-4o mini and 41.2% for Qwen3-Coder 480B-A35B Instruct.
  • GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
  • Qwen3-Coder 480B-A35B Instruct accepts more context: 262K tokens versus 128K.
  • Qwen3-Coder 480B-A35B Instruct has downloadable open weights; the other is API-only.

Side by side

GPT-4o miniQwen3-Coder 480B-A35B Instruct
ProviderOpenAIAlibaba (Qwen)
Noometry Index25.538.1
Released2024-07-182025-04
WeightsProprietaryOpen
Context window128K262K
Max output16K66K
Input $ / M tokens$0.15$1.50
Output $ / M tokens$0.60$7.50
Results tracked6025

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

Category by category

Coding Qwen3-Coder 480B-A35B Instruct leads

GPT-4o mini: 22.0 (#335), Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)

BenchmarkGPT-4o miniQwen3-Coder 480B-A35B Instruct
WeirdML11.8%41.2%
LMArena Coding12901412
SWE-bench Verified (bash only)—55.4%
Aider Polyglot3.6%—
LMArena WebDev—1275
GSO—4.9%
BigCodeBench Instruct46.1%—
LiveBench Coding43.1%—
BigCodeBench Complete57.4%—
ALE-Bench—461.45
AlgoTune—1.44
HumanEval+83.5%—
MBPP+72.2%—

Agentic & Tool Use GPT-4o mini leads

GPT-4o mini: 27.5 (#101), Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)

BenchmarkGPT-4o miniQwen3-Coder 480B-A35B Instruct
Terminal-Bench—27.2%
BALROG17.4%—

Reasoning Qwen3-Coder 480B-A35B Instruct leads

GPT-4o mini: 8.7 (#347), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)

BenchmarkGPT-4o miniQwen3-Coder 480B-A35B Instruct
Kagi LLM Benchmark28.8%49.5%
LMArena Hard Prompts12671372
ARC-AGI-20%—
SimpleBench10.7%—
Chess Puzzles0%—
LiveBench Reasoning32.8%—
Mystery Game Puzzles12%—
DTBench54.4%—
LiveBench Data Analysis50%—
LMCA10.4%—
Epoch Capabilities Index126.56—
LiveBench41.3%—
PIQA88.7%—

Math Qwen3-Coder 480B-A35B Instruct leads

GPT-4o mini: 10.4 (#314), Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)

BenchmarkGPT-4o miniQwen3-Coder 480B-A35B Instruct
LMArena Math12671365
FrontierMath (Tiers 1-3)0.7%—
OTIS Mock AIME 2024-20256.9%—
Omni-MATH28%—
LiveBench Math36.3%—
MATH Level 552.6%—
GSM8K91.3%—

Knowledge Qwen3-Coder 480B-A35B Instruct leads

GPT-4o mini: 17.7 (#284), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)

BenchmarkGPT-4o miniQwen3-Coder 480B-A35B Instruct
LMArena Expert12351338
GPQA Diamond37.7%—
SimpleQA Verified8.3%—
MMLU-Pro60.3%—
Confabulations37.2%—
GPQA (HELM)36.8%—
BoolQ88.7%—
MMLU81.8%—

Multimodal Not comparable

GPT-4o mini: 25.9 (#122), Qwen3-Coder 480B-A35B Instruct: —

BenchmarkGPT-4o miniQwen3-Coder 480B-A35B Instruct
LMArena Vision1066—
Video-MME64.8%—
GeoBench64%—
VPCT34%—

Multilingual Qwen3-Coder 480B-A35B Instruct leads

GPT-4o mini: 42.0 (#199), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)

BenchmarkGPT-4o miniQwen3-Coder 480B-A35B Instruct
LMArena Non-English12661346
LMArena Chinese12651357
LMArena French12971398
LMArena German12721325
LMArena Japanese12161310
LMArena Korean11951305
LMArena Russian12751366
LMArena Spanish12761360

Instruction Following Qwen3-Coder 480B-A35B Instruct leads

GPT-4o mini: 61.9 (#239), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)

BenchmarkGPT-4o miniQwen3-Coder 480B-A35B Instruct
LMArena Instruction Following12581355
LiveBench Instruction Following56.8%—
IFEval78.2%—

Long Context Qwen3-Coder 480B-A35B Instruct leads

GPT-4o mini: 39.1 (#186), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)

BenchmarkGPT-4o miniQwen3-Coder 480B-A35B Instruct
LMArena Longer Query12891378

Writing & Preference Qwen3-Coder 480B-A35B Instruct leads

GPT-4o mini: 39.5 (#248), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)

BenchmarkGPT-4o miniQwen3-Coder 480B-A35B Instruct
LMArena Text12861357
LMArena Creative Writing12681333
LMArena Multi-Turn12851365
Short-Story Creative Writing67.2%—
EQ-Bench Creative Writing873—
WildBench79.1%—
LiveBench Language28.6%—

Frequently asked questions

Is GPT-4o mini better than Qwen3-Coder 480B-A35B Instruct?

Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 38.1 to 25.5 on the Noometry Index. GPT-4o mini costs 11× less per token, which makes it the better buy when Qwen3-Coder 480B-A35B Instruct's lead doesn't matter for your workload.

Which is cheaper, GPT-4o mini or Qwen3-Coder 480B-A35B Instruct?

GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.

Is GPT-4o mini or Qwen3-Coder 480B-A35B Instruct better for coding?

Qwen3-Coder 480B-A35B Instruct scores higher on coding benchmarks: 35.5 versus 22.0 in the Noometry coding category.

Which has the bigger context window?

Qwen3-Coder 480B-A35B Instruct does, with 262K tokens against 128K.

How many benchmarks do GPT-4o mini and Qwen3-Coder 480B-A35B Instruct share?

19 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.

Related comparisons

Go deeper