Model comparison

GPT-5 Pro vs Qwen3.5 35B-A3B

GPT-5 Pro is the stronger model overall, scoring 46.4 to 42.0 on the Noometry Index. Qwen3.5 35B-A3B costs 60× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.

Last verified October 12, 2026. 1 shared benchmarks.

GPT-5 Pro OpenAI

46.4

Rank #64 Confirmed

Qwen3.5 35B-A3B

Alibaba (Qwen)

42.0

Rank #123 Confirmed

Summary

They share 1 benchmark with published results for both. GPT-5 Pro scores higher in 4 categories and Qwen3.5 35B-A3B in 0 categories; 4 gaps are clear of the uncertainty.
The widest gap is in reasoning, where GPT-5 Pro leads 38.9 to 24.6.
Qwen3.5 35B-A3B is cheaper at $0.25 / $2 per million input/output tokens, against $15 / $120 for GPT-5 Pro.
GPT-5 Pro accepts more context: 400K tokens versus 262K.
Qwen3.5 35B-A3B has downloadable open weights; the other is API-only.

Side by side

GPT-5 Pro and Qwen3.5 35B-A3B specifications
	GPT-5 Pro	Qwen3.5 35B-A3B
Provider	OpenAI	Alibaba (Qwen)
Noometry Index	46.4	42.0
Released	2025-10-06	2026-02-01
Weights	Proprietary	Open
Context window	400K	262K
Max output	272K	66K
Input $ / M tokens	$15	$0.25
Output $ / M tokens	$120	$2
Results tracked	12	28

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

Category by category

Coding GPT-5 Pro leads

GPT-5 Pro: 44.0 (#80), Qwen3.5 35B-A3B: 33.8 (#251)

Coding benchmarks
Benchmark	GPT-5 Pro	Qwen3.5 35B-A3B
LMArena WebDev	—	1254
SciCode	—	29.3%
WeirdML	60.4%	—
LMArena Coding	—	1410
AlgoTune	1.31	—

Reasoning GPT-5 Pro leads

GPT-5 Pro: 38.9 (#62), Qwen3.5 35B-A3B: 24.6 (#161)

Reasoning benchmarks
Benchmark	GPT-5 Pro	Qwen3.5 35B-A3B
Epoch Capabilities Index	150.28	142.52
ARC-AGI-2	18.3%	—
SimpleBench	61.6%	—
Kagi LLM Benchmark	76.8%	—
ARC-AGI-1	70.2%	—
CritPt	—	0.6%
Chess Puzzles	—	10%
EnigmaEval	18.8%	—
LMArena Hard Prompts	—	1400
DTBench	—	80%
LMCA	—	29.5%

Math GPT-5 Pro leads

GPT-5 Pro: 48.5 (#63), Qwen3.5 35B-A3B: 39.9 (#97)

Math benchmarks
Benchmark	GPT-5 Pro	Qwen3.5 35B-A3B
FrontierMath (Tiers 1-3)	55.8%	—
FrontierMath Tier 4	19.5%	—
MathArena Final-Answer Competitions	—	56%
OTIS Mock AIME 2024-2025	—	70%
LMArena Math	—	1404
FrontierMath Tier 4 (v1)	14.6%	—

Knowledge GPT-5 Pro leads

GPT-5 Pro: 56.7 (#42), Qwen3.5 35B-A3B: 47.8 (#79)

Knowledge benchmarks
Benchmark	GPT-5 Pro	Qwen3.5 35B-A3B
GPQA Diamond	—	83.5%
Humanity's Last Exam	31.6%	—
Vectara Hallucination Rate	—	10.5%
LMArena Expert	—	1408

Multilingual Not comparable

GPT-5 Pro: —, Qwen3.5 35B-A3B: 50.0 (#127)

Multilingual benchmarks
Benchmark	GPT-5 Pro	Qwen3.5 35B-A3B
LMArena Non-English	—	1378
LMArena Chinese	—	1457
LMArena French	—	1412
LMArena German	—	1367
LMArena Japanese	—	1325
LMArena Korean	—	1356
LMArena Russian	—	1376
LMArena Spanish	—	1392

Instruction Following Not comparable

GPT-5 Pro: —, Qwen3.5 35B-A3B: 72.8 (#128)

Instruction Following benchmarks
Benchmark	GPT-5 Pro	Qwen3.5 35B-A3B
LMArena Instruction Following	—	1379

Long Context Not comparable

GPT-5 Pro: —, Qwen3.5 35B-A3B: 42.4 (#127)

Long Context benchmarks
Benchmark	GPT-5 Pro	Qwen3.5 35B-A3B
LMArena Longer Query	—	1389

Writing & Preference Not comparable

GPT-5 Pro: —, Qwen3.5 35B-A3B: 57.9 (#124)

Writing & Preference benchmarks
Benchmark	GPT-5 Pro	Qwen3.5 35B-A3B
LMArena Text	—	1395
LMArena Creative Writing	—	1346
LMArena Multi-Turn	—	1390

Frequently asked questions

Is GPT-5 Pro better than Qwen3.5 35B-A3B?

Which is cheaper, GPT-5 Pro or Qwen3.5 35B-A3B?

Qwen3.5 35B-A3B is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; GPT-5 Pro lists at $15 and $120.

Is GPT-5 Pro or Qwen3.5 35B-A3B better for coding?

GPT-5 Pro scores higher on coding benchmarks: 44.0 versus 33.8 in the Noometry coding category.

Which has the bigger context window?

GPT-5 Pro does, with 400K tokens against 262K.

How many benchmarks do GPT-5 Pro and Qwen3.5 35B-A3B share?

1 benchmark has published results for both models. GPT-5 Pro has 12 scored results on Noometry and Qwen3.5 35B-A3B has 28.