Model comparison

GPT-5.2 vs Qwen2.5 7B Instruct

GPT-5.2 is the stronger model overall, scoring 54.1 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 16× 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. 6 shared benchmarks.

GPT-5.2 OpenAI

54.1

Rank #34 Confirmed

Qwen2.5 7B Instruct

Alibaba (Qwen)

29.0

Rank #320 Confirmed

Summary

They share 6 benchmarks with published results for both. GPT-5.2 scores higher in 7 categories and Qwen2.5 7B Instruct in 0 categories; 7 gaps are clear of the uncertainty.
The widest gap is in math, where GPT-5.2 leads 60.0 to 12.6.
The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 96.1% for GPT-5.2 and 2.5% for Qwen2.5 7B Instruct.
Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $1.75 / $14 for GPT-5.2.
GPT-5.2 accepts more context: 400K tokens versus 131K.
Qwen2.5 7B Instruct has downloadable open weights; the other is API-only.

Side by side

GPT-5.2 and Qwen2.5 7B Instruct specifications
	GPT-5.2	Qwen2.5 7B Instruct
Provider	OpenAI	Alibaba (Qwen)
Noometry Index	54.1	29.0
Released	2025-12-11	2024-09
Weights	Proprietary	Open
Context window	400K	131K
Max output	128K	8K
Input $ / M tokens	$1.75	$0.17
Output $ / M tokens	$14	$0.70
Results tracked	67	15

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

Category by category

Coding GPT-5.2 leads

GPT-5.2: 51.6 (#37), Qwen2.5 7B Instruct: 36.5 (#208)

Coding benchmarks
Benchmark	GPT-5.2	Qwen2.5 7B Instruct
SWE-bench Verified	73.8%	—
SWE-bench Verified (bash only)	72.8%	—
LMArena WebDev	1416	—
SWE-bench Multilingual	66.7%	—
GSO	27.4%	—
WeirdML	72.2%	—
BigCodeBench Instruct	—	37.6%
LMArena Coding	1447	—
BigCodeBench Complete	—	46.1%
ALE-Bench	1,294	—
AlgoTune	2.05	—

Agentic & Tool Use GPT-5.2 leads

GPT-5.2: 40.2 (#24), Qwen2.5 7B Instruct: 23.8 (#124)

Agentic & Tool Use benchmarks
Benchmark	GPT-5.2	Qwen2.5 7B 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%	—
BALROG	—	7.8%
LMArena Search	1207	—
METR Time Horizons	75.3%	—
Vending-Bench 2	3,591	—

Reasoning GPT-5.2 leads

GPT-5.2: 50.2 (#35), Qwen2.5 7B Instruct: 14.8 (#322)

Reasoning benchmarks
Benchmark	GPT-5.2	Qwen2.5 7B Instruct
Chess Puzzles	49%	0%
DTBench	90.9%	47.7%
LMCA	43.9%	6.4%
Epoch Capabilities Index	153.45	118.51
ARC-AGI-2	52.9%	—
SimpleBench	45.8%	—
Kagi LLM Benchmark	73.3%	—
NYT Connections (extended)	83.6%	—
ARC-AGI-1	86.2%	—
EnigmaEval	10.4%	—
EBR-Bench	23%	—
LMArena Hard Prompts	1445	—
Mystery Game Puzzles	23%	—
ForecastBench	60.1	—

Math GPT-5.2 leads

GPT-5.2: 60.0 (#38), Qwen2.5 7B Instruct: 12.6 (#306)

Math benchmarks
Benchmark	GPT-5.2	Qwen2.5 7B Instruct
OTIS Mock AIME 2024-2025	96.1%	2.5%
FrontierMath (Tiers 1-3)	67.4%	—
FrontierMath Tier 4	31.7%	—
MathArena Final-Answer Competitions	72%	—
ProofBench	15%	—
Omni-MATH	—	29.4%
LMArena Math	1440	—
FrontierMath (Feb 2025 set)	40.7%	—
FrontierMath Tier 4 (v1)	18.8%	—

Knowledge GPT-5.2 leads

GPT-5.2: 59.3 (#32), Qwen2.5 7B Instruct: 17.0 (#286)

Knowledge benchmarks
Benchmark	GPT-5.2	Qwen2.5 7B Instruct
GPQA Diamond	91.4%	35.5%
Humanity's Last Exam	27.8%	—
SimpleQA Verified	37.1%	—
MMLU-Pro	—	53.9%
Vectara Hallucination Rate	8.4%	—
GPQA (HELM)	—	34.1%
LMArena Expert	1445	—
MMLU	—	72.9%

Multimodal Not comparable

GPT-5.2: 51.3 (#7), Qwen2.5 7B Instruct: —

Multimodal benchmarks
Benchmark	GPT-5.2	Qwen2.5 7B Instruct
LMArena Vision	1268	—
VPCT	84%	—
Furniture Assembly	38.3%	—
LMArena Document	1405	—

Multilingual Not comparable

GPT-5.2: 53.4 (#67), Qwen2.5 7B Instruct: —

Multilingual benchmarks
Benchmark	GPT-5.2	Qwen2.5 7B Instruct
LMArena Non-English	1425	—
LMArena Chinese	1460	—
LMArena French	1455	—
LMArena German	1448	—
LMArena Japanese	1420	—
LMArena Korean	1392	—
LMArena Russian	1440	—
LMArena Spanish	1433	—

Instruction Following GPT-5.2 leads

GPT-5.2: 74.7 (#89), Qwen2.5 7B Instruct: 63.2 (#231)

Instruction Following benchmarks
Benchmark	GPT-5.2	Qwen2.5 7B Instruct
IFEval	—	74.1%
LMArena Instruction Following	1417	—

Long Context Not comparable

GPT-5.2: 44.0 (#78), Qwen2.5 7B Instruct: —

Long Context benchmarks
Benchmark	GPT-5.2	Qwen2.5 7B Instruct
CL-bench	18.2%	—
LMArena Longer Query	1428	—

Writing & Preference GPT-5.2 leads

GPT-5.2: 66.8 (#32), Qwen2.5 7B Instruct: 48.8 (#195)

Writing & Preference benchmarks
Benchmark	GPT-5.2	Qwen2.5 7B Instruct
LMArena Text	1439	—
LMArena Creative Writing	1401	—
EQ-Bench Creative Writing	1703	—
WildBench	—	73.1%
LMArena Multi-Turn	1458	—

Frequently asked questions

Is GPT-5.2 better than Qwen2.5 7B Instruct?

Which is cheaper, GPT-5.2 or Qwen2.5 7B Instruct?

Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; GPT-5.2 lists at $1.75 and $14.

Is GPT-5.2 or Qwen2.5 7B Instruct better for coding?

GPT-5.2 scores higher on coding benchmarks: 51.6 versus 36.5 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 Qwen2.5 7B Instruct share?

6 benchmarks have published results for both models. GPT-5.2 has 67 scored results on Noometry and Qwen2.5 7B Instruct has 15.