Model comparison

GPT-5.2 vs Qwen3-Next 80B-A3B Instruct

GPT-5.2 is the stronger model overall, scoring 54.1 to 42.5 on the Noometry Index. Qwen3-Next 80B-A3B Instruct costs 5.5× less per token, which makes it the better buy when GPT-5.2's lead doesn't matter for your workload.

Last verified October 10, 2026. 19 shared benchmarks.

GPT-5.2 OpenAI

54.1

Rank #31 Confirmed

Qwen3-Next 80B-A3B Instruct

Alibaba (Qwen)

42.5

Rank #100 Confirmed

Summary

They share 19 benchmarks with published results for both. GPT-5.2 scores higher in 8 categories and Qwen3-Next 80B-A3B Instruct in 0 categories; 8 gaps are clear of the uncertainty.
The widest gap is in math, where GPT-5.2 leads 59.8 to 36.3.
The biggest single-benchmark swing is Kagi LLM Benchmark: 73.3% for GPT-5.2 and 66.7% for Qwen3-Next 80B-A3B Instruct.
Qwen3-Next 80B-A3B Instruct is cheaper at $0.50 / $2 per million input/output tokens, against $1.75 / $14 for GPT-5.2.
GPT-5.2 accepts more context: 400K tokens versus 131K.
Qwen3-Next 80B-A3B Instruct has downloadable open weights; the other is API-only.

Side by side

GPT-5.2 and Qwen3-Next 80B-A3B Instruct specifications
	GPT-5.2	Qwen3-Next 80B-A3B Instruct
Provider	OpenAI	Alibaba (Qwen)
Noometry Index	54.1	42.5
Released	2025-12-11	2025-09
Weights	Proprietary	Open
Context window	400K	131K
Max output	128K	33K
Input $ / M tokens	$1.75	$0.50
Output $ / M tokens	$14	$2
Results tracked	67	25

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

Category by category

Coding GPT-5.2 leads

GPT-5.2: 52.2 (#32), Qwen3-Next 80B-A3B Instruct: 41.9 (#101)

Coding benchmarks
Benchmark	GPT-5.2	Qwen3-Next 80B-A3B Instruct
LMArena Coding	1447	1441
SWE-bench Verified	73.8%	—
SWE-bench Verified (bash only)	72.8%	—
LMArena WebDev	1415	—
SWE-bench Multilingual	66.7%	—
GSO	27.4%	—
WeirdML	72.2%	—
ALE-Bench	1,294	—
AlgoTune	2.05	—

Agentic & Tool Use Not comparable

GPT-5.2: 40.0 (#24), Qwen3-Next 80B-A3B Instruct: —

Agentic & Tool Use benchmarks
Benchmark	GPT-5.2	Qwen3-Next 80B-A3B Instruct
Terminal-Bench	64.9%	—
Berkeley Function Calling Leaderboard	55.9%	—
GDPval	49.7%	—
Remote Labor Index	2.5%	—
τ²-bench Airline	83%	—
τ²-bench Banking	32.2%	—
τ²-bench Retail	81.6%	—
τ²-bench Telecom	89.7%	—
DeepResearch Bench	41.1%	—
LMArena Search	1207	—
METR Time Horizons	75.3%	—
Vending-Bench 2	3,591	—

Reasoning GPT-5.2 leads

GPT-5.2: 50.1 (#33), Qwen3-Next 80B-A3B Instruct: 30.1 (#79)

Reasoning benchmarks
Benchmark	GPT-5.2	Qwen3-Next 80B-A3B Instruct
Kagi LLM Benchmark	73.3%	66.7%
LMArena Hard Prompts	1445	1428
ARC-AGI-2	52.9%	—
SimpleBench	45.8%	—
NYT Connections (extended)	83.6%	—
ARC-AGI-1	86.2%	—
Chess Puzzles	49%	—
EnigmaEval	10.4%	—
EBR-Bench	23%	—
Mystery Game Puzzles	23%	—
DTBench	90.9%	—
LMCA	43.9%	—
Epoch Capabilities Index	153.45	—
ForecastBench	60.1	—

Math GPT-5.2 leads

GPT-5.2: 59.8 (#32), Qwen3-Next 80B-A3B Instruct: 36.3 (#118)

Math benchmarks
Benchmark	GPT-5.2	Qwen3-Next 80B-A3B Instruct
LMArena Math	1439	1440
FrontierMath (Tiers 1-3)	67.4%	—
FrontierMath Tier 4	31.7%	—
MathArena Final-Answer Competitions	72%	—
OTIS Mock AIME 2024-2025	96.1%	—
ProofBench	15%	—
Omni-MATH	—	46.7%
FrontierMath (Feb 2025 set)	40.7%	—
FrontierMath Tier 4 (v1)	18.8%	—

Knowledge GPT-5.2 leads

GPT-5.2: 59.2 (#29), Qwen3-Next 80B-A3B Instruct: 41.3 (#102)

Knowledge benchmarks
Benchmark	GPT-5.2	Qwen3-Next 80B-A3B Instruct
Vectara Hallucination Rate	8.4%	9.3%
LMArena Expert	1445	1416
GPQA Diamond	91.4%	—
Humanity's Last Exam	27.8%	—
SimpleQA Verified	37.1%	—
MMLU-Pro	—	78.6%
GPQA (HELM)	—	63%

Multimodal Not comparable

GPT-5.2: 50.9 (#7), Qwen3-Next 80B-A3B Instruct: —

Multimodal benchmarks
Benchmark	GPT-5.2	Qwen3-Next 80B-A3B Instruct
LMArena Vision	1268	—
VPCT	84%	—
Furniture Assembly	38.3%	—
LMArena Document	1405	—

Multilingual GPT-5.2 leads

GPT-5.2: 53.6 (#63), Qwen3-Next 80B-A3B Instruct: 52.3 (#88)

Multilingual benchmarks
Benchmark	GPT-5.2	Qwen3-Next 80B-A3B Instruct
LMArena Non-English	1425	1407
LMArena Chinese	1460	1461
LMArena French	1456	1415
LMArena German	1448	1416
LMArena Japanese	1421	1398
LMArena Korean	1390	1366
LMArena Russian	1440	1403
LMArena Spanish	1433	1436

Instruction Following GPT-5.2 leads

GPT-5.2: 74.9 (#83), Qwen3-Next 80B-A3B Instruct: 71.0 (#154)

Instruction Following benchmarks
Benchmark	GPT-5.2	Qwen3-Next 80B-A3B Instruct
LMArena Instruction Following	1417	1388
IFEval	—	81%

Long Context GPT-5.2 leads

GPT-5.2: 44.0 (#74), Qwen3-Next 80B-A3B Instruct: 37.0 (#218)

Long Context benchmarks
Benchmark	GPT-5.2	Qwen3-Next 80B-A3B Instruct
LMArena Longer Query	1428	1403
Fiction.LiveBench	—	55.6%
CL-bench	18.2%	—

Writing & Preference GPT-5.2 leads

GPT-5.2: 67.0 (#30), Qwen3-Next 80B-A3B Instruct: 58.2 (#116)

Writing & Preference benchmarks
Benchmark	GPT-5.2	Qwen3-Next 80B-A3B Instruct
LMArena Text	1439	1417
LMArena Creative Writing	1402	1333
LMArena Multi-Turn	1458	1415
EQ-Bench Creative Writing	1703	—
WildBench	—	80.7%

Frequently asked questions

Is GPT-5.2 better than Qwen3-Next 80B-A3B Instruct?

Which is cheaper, GPT-5.2 or Qwen3-Next 80B-A3B Instruct?

Qwen3-Next 80B-A3B Instruct is cheaper. It lists at $0.50 per million input tokens and $2 per million output tokens; GPT-5.2 lists at $1.75 and $14.

Is GPT-5.2 or Qwen3-Next 80B-A3B Instruct better for coding?

GPT-5.2 scores higher on coding benchmarks: 52.2 versus 41.9 in the Noometry coding category.

Which has the bigger context window?

GPT-5.2 does, with 400K tokens against 131K.

How many benchmarks do GPT-5.2 and Qwen3-Next 80B-A3B Instruct share?

19 benchmarks have published results for both models. GPT-5.2 has 67 scored results on Noometry and Qwen3-Next 80B-A3B Instruct has 25.