Model comparison

GPT-5.4 vs Qwen3-Coder 480B-A35B Instruct

GPT-5.4 is the stronger model overall, scoring 59.4 to 38.1 on the Noometry Index. Qwen3-Coder 480B-A35B Instruct costs 1.9× less per token, which makes it the better buy when GPT-5.4's lead doesn't matter for your workload.

Last verified October 10, 2026. 24 shared benchmarks.

GPT-5.4 OpenAI

59.4

Rank #16 Confirmed

Qwen3-Coder 480B-A35B Instruct

Alibaba (Qwen)

38.1

Rank #190 Confirmed

Summary

They share 24 benchmarks with published results for both. GPT-5.4 scores higher in 9 categories and Qwen3-Coder 480B-A35B Instruct in 0 categories; 9 gaps are clear of the uncertainty.
The widest gap is in reasoning, where GPT-5.4 leads 61.8 to 25.5.
The biggest single-benchmark swing is Terminal-Bench: 81.8% for GPT-5.4 and 27.2% for Qwen3-Coder 480B-A35B Instruct.
Qwen3-Coder 480B-A35B Instruct is cheaper at $1.50 / $7.50 per million input/output tokens, against $2.50 / $15 for GPT-5.4.
GPT-5.4 accepts more context: 1.05M tokens versus 262K.
Qwen3-Coder 480B-A35B Instruct has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 and Qwen3-Coder 480B-A35B Instruct specifications
	GPT-5.4	Qwen3-Coder 480B-A35B Instruct
Provider	OpenAI	Alibaba (Qwen)
Noometry Index	59.4	38.1
Released	2026-03-05	2025-04
Weights	Proprietary	Open
Context window	1.05M	262K
Max output	128K	66K
Input $ / M tokens	$2.50	$1.50
Output $ / M tokens	$15	$7.50
Results tracked	68	25

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

Category by category

Coding GPT-5.4 leads

GPT-5.4: 52.6 (#33), Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)

Coding benchmarks
Benchmark	GPT-5.4	Qwen3-Coder 480B-A35B Instruct
LMArena WebDev	1465	1275
GSO	31.4%	4.9%
WeirdML	77.7%	41.2%
LMArena Coding	1497	1412
ALE-Bench	1,607	461.45
AlgoTune	1.85	1.44
SWE-bench Verified	76.9%	—
DeepSWE	51.8%	—
SWE-bench Verified (bash only)	—	55.4%
SciCode	56.6%	—
MirrorCode	15.6%	—

Agentic & Tool Use GPT-5.4 leads

GPT-5.4: 46.5 (#13), Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)

Agentic & Tool Use benchmarks
Benchmark	GPT-5.4	Qwen3-Coder 480B-A35B Instruct
Terminal-Bench	81.8%	27.2%
APEX-Agents	52.4%	—
τ²-bench Banking	39.4%	—
DeepResearch Bench	35.1%	—
PostTrainBench	19%	—
GBAEval	45.1%	—
LMArena Search	1197	—
METR Time Horizons	74.3%	—
Vending-Bench 2	6,144	—

Reasoning GPT-5.4 leads

GPT-5.4: 61.8 (#19), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)

Reasoning benchmarks
Benchmark	GPT-5.4	Qwen3-Coder 480B-A35B Instruct
Kagi LLM Benchmark	63.8%	49.5%
LMArena Hard Prompts	1485	1372
ARC-AGI-2	74%	—
NYT Connections (extended)	91.3%	—
ARC-AGI-1	93.7%	—
CritPt	23.4%	—
Chess Puzzles	44%	—
EnigmaEval	16%	—
Thematic Generalization	80%	—
EBR-Bench	25.4%	—
Mystery Game Puzzles	37%	—
DTBench	94.4%	—
LMCA	52%	—
Epoch Capabilities Index	156.81	—
ForecastBench	59.5	—

Math GPT-5.4 leads

GPT-5.4: 73.5 (#19), Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)

Math benchmarks
Benchmark	GPT-5.4	Qwen3-Coder 480B-A35B Instruct
LMArena Math	1488	1365
FrontierMath (Tiers 1-3)	78.6%	—
FrontierMath Tier 4	49%	—
MathArena Final-Answer Competitions	83.1%	—
OTIS Mock AIME 2024-2025	97.8%	—
ProofBench	56%	—
FrontierMath (Feb 2025 set)	47.6%	—
FrontierMath Tier 4 (v1)	27.1%	—

Knowledge GPT-5.4 leads

GPT-5.4: 65.3 (#14), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)

Knowledge benchmarks
Benchmark	GPT-5.4	Qwen3-Coder 480B-A35B Instruct
LMArena Expert	1507	1338
GPQA Diamond	93.3%	—
Humanity's Last Exam	36.2%	—
SimpleQA Verified	45.1%	—
Vectara Hallucination Rate	7%	—

Multimodal Not comparable

GPT-5.4: 43.7 (#20), Qwen3-Coder 480B-A35B Instruct: —

Multimodal benchmarks
Benchmark	GPT-5.4	Qwen3-Coder 480B-A35B Instruct
LMArena Vision	1303	—
Blueprint-Bench 2	27.1%	—
Furniture Assembly	37.5%	—
LMArena Document	1471	—

Multilingual GPT-5.4 leads

GPT-5.4: 56.2 (#23), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)

Multilingual benchmarks
Benchmark	GPT-5.4	Qwen3-Coder 480B-A35B Instruct
LMArena Non-English	1465	1346
LMArena Chinese	1519	1357
LMArena French	1493	1398
LMArena German	1472	1325
LMArena Japanese	1485	1310
LMArena Korean	1448	1305
LMArena Russian	1480	1366
LMArena Spanish	1454	1360

Instruction Following GPT-5.4 leads

GPT-5.4: 77.1 (#27), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)

Instruction Following benchmarks
Benchmark	GPT-5.4	Qwen3-Coder 480B-A35B Instruct
LMArena Instruction Following	1469	1355

Long Context GPT-5.4 leads

GPT-5.4: 50.3 (#8), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)

Long Context benchmarks
Benchmark	GPT-5.4	Qwen3-Coder 480B-A35B Instruct
LMArena Longer Query	1473	1378
CL-bench	27.9%	—
CL-bench Life	21.7%	—

Writing & Preference GPT-5.4 leads

GPT-5.4: 71.9 (#17), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)

Writing & Preference benchmarks
Benchmark	GPT-5.4	Qwen3-Coder 480B-A35B Instruct
LMArena Text	1469	1357
LMArena Creative Writing	1439	1333
LMArena Multi-Turn	1482	1365
EQ-Bench Creative Writing	1840	—
EQ-Bench 4	1272	—

Frequently asked questions

Is GPT-5.4 better than Qwen3-Coder 480B-A35B Instruct?

Which is cheaper, GPT-5.4 or Qwen3-Coder 480B-A35B Instruct?

Qwen3-Coder 480B-A35B Instruct is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; GPT-5.4 lists at $2.50 and $15.

Is GPT-5.4 or Qwen3-Coder 480B-A35B Instruct better for coding?

GPT-5.4 scores higher on coding benchmarks: 52.6 versus 35.5 in the Noometry coding category.

Which has the bigger context window?

GPT-5.4 does, with 1.05M tokens against 262K.

How many benchmarks do GPT-5.4 and Qwen3-Coder 480B-A35B Instruct share?

24 benchmarks have published results for both models. GPT-5.4 has 68 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.