Noometry

Model comparison

GPT-5.4 nano vs Qwen3.6 35B-A3B

GPT-5.4 nano is the stronger model overall, scoring 41.9 to 37.6 on the Noometry Index.

Last verified . 11 shared benchmarks.

GPT-5.4 nano OpenAI

41.9

Rank #125 Confirmed

Qwen3.6 35B-A3B Alibaba (Qwen)

37.6

Rank #201 Confirmed

Summary

  • They share 11 benchmarks with published results for both. GPT-5.4 nano scores higher in 2 categories and Qwen3.6 35B-A3B in 2 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3.6 35B-A3B leads 51.3 to 41.9.
  • The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 44.9% for GPT-5.4 nano and 20.4% for Qwen3.6 35B-A3B.
  • GPT-5.4 nano is cheaper at $0.20 / $1.25 per million input/output tokens, against $0.25 / $1.49 for Qwen3.6 35B-A3B.
  • GPT-5.4 nano accepts more context: 400K tokens versus 262K.
  • Qwen3.6 35B-A3B has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 nanoQwen3.6 35B-A3B
ProviderOpenAIAlibaba (Qwen)
Noometry Index41.937.6
Released2026-03-172026-04-01
WeightsProprietaryOpen
Context window400K262K
Max output128K66K
Input $ / M tokens$0.20$0.25
Output $ / M tokens$1.25$1.49
Results tracked4014

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

Category by category

Coding GPT-5.4 nano leads

GPT-5.4 nano: 43.6 (#84), Qwen3.6 35B-A3B: 37.2 (#196)

BenchmarkGPT-5.4 nanoQwen3.6 35B-A3B
SciCode46.9%35.8%
WeirdML49.2%34.5%
LMArena Coding1405—
ALE-Bench1,005—

Agentic & Tool Use Not comparable

GPT-5.4 nano: —, Qwen3.6 35B-A3B: 22.1 (#134)

BenchmarkGPT-5.4 nanoQwen3.6 35B-A3B
Terminal-Bench—23%

Reasoning Qwen3.6 35B-A3B leads

GPT-5.4 nano: 23.7 (#173), Qwen3.6 35B-A3B: 28.0 (#109)

BenchmarkGPT-5.4 nanoQwen3.6 35B-A3B
CritPt9.3%0.3%
Chess Puzzles30%26%
Mystery Game Puzzles9%22%
DTBench80.3%73.9%
LMCA36.9%29.7%
Epoch Capabilities Index145.81143.93
ARC-AGI-25.7%—
Kagi LLM Benchmark39.7%—
NYT Connections (extended)—41.6%
ARC-AGI-151.5%—
LMArena Hard Prompts1381—
Surface Evolver Bench—44.4%
ForecastBench57.3—

Math GPT-5.4 nano leads

GPT-5.4 nano: 40.9 (#88), Qwen3.6 35B-A3B: 38.9 (#121)

BenchmarkGPT-5.4 nanoQwen3.6 35B-A3B
FrontierMath (Tiers 1-3)44.9%20.4%
OTIS Mock AIME 2024-202587.8%86.7%
FrontierMath Tier 412.2%—
ProofBench5%—
LMArena Math1406—
FrontierMath (Feb 2025 set)25.9%—
FrontierMath Tier 4 (v1)6.3%—

Knowledge Qwen3.6 35B-A3B leads

GPT-5.4 nano: 41.9 (#103), Qwen3.6 35B-A3B: 51.3 (#68)

BenchmarkGPT-5.4 nanoQwen3.6 35B-A3B
GPQA Diamond78.5%84.8%
SimpleQA Verified11.7%—
Vectara Hallucination Rate3.1%—
LMArena Expert1396—

Multimodal Not comparable

GPT-5.4 nano: 36.7 (#78), Qwen3.6 35B-A3B: —

BenchmarkGPT-5.4 nanoQwen3.6 35B-A3B
LMArena Vision1196—

Multilingual Not comparable

GPT-5.4 nano: 48.6 (#140), Qwen3.6 35B-A3B: —

BenchmarkGPT-5.4 nanoQwen3.6 35B-A3B
LMArena Non-English1359—
LMArena Chinese1392—
LMArena French1396—
LMArena German1367—
LMArena Japanese1343—
LMArena Korean1320—
LMArena Russian1363—
LMArena Spanish1371—

Instruction Following Not comparable

GPT-5.4 nano: 71.9 (#144), Qwen3.6 35B-A3B: —

BenchmarkGPT-5.4 nanoQwen3.6 35B-A3B
LMArena Instruction Following1362—

Long Context Not comparable

GPT-5.4 nano: 41.6 (#137), Qwen3.6 35B-A3B: —

BenchmarkGPT-5.4 nanoQwen3.6 35B-A3B
LMArena Longer Query1366—

Writing & Preference Not comparable

GPT-5.4 nano: 55.7 (#142), Qwen3.6 35B-A3B: —

BenchmarkGPT-5.4 nanoQwen3.6 35B-A3B
LMArena Text1372—
LMArena Creative Writing1314—
LMArena Multi-Turn1382—

Frequently asked questions

Is GPT-5.4 nano better than Qwen3.6 35B-A3B?

GPT-5.4 nano is the stronger model overall, scoring 41.9 to 37.6 on the Noometry Index.

Which is cheaper, GPT-5.4 nano or Qwen3.6 35B-A3B?

GPT-5.4 nano is cheaper. It lists at $0.20 per million input tokens and $1.25 per million output tokens; Qwen3.6 35B-A3B lists at $0.25 and $1.49.

Is GPT-5.4 nano or Qwen3.6 35B-A3B better for coding?

GPT-5.4 nano scores higher on coding benchmarks: 43.6 versus 37.2 in the Noometry coding category.

Which has the bigger context window?

GPT-5.4 nano does, with 400K tokens against 262K.

How many benchmarks do GPT-5.4 nano and Qwen3.6 35B-A3B share?

11 benchmarks have published results for both models. GPT-5.4 nano has 40 scored results on Noometry and Qwen3.6 35B-A3B has 14.

Related comparisons

Go deeper