Noometry

Model comparison

GPT-5 vs Qwen3.8 Max

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 50.9 on the Noometry Index.

Last verified . 32 shared benchmarks.

GPT-5 OpenAI

50.9

Rank #45 Confirmed

Qwen3.8 Max Alibaba (Qwen)

56.8

Rank #22 Confirmed

Summary

  • They share 32 benchmarks with published results for both. GPT-5 scores higher in 2 categories and Qwen3.8 Max in 8 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in long context, where GPT-5 leads 69.5 to 45.6.
  • The biggest single-benchmark swing is ProofBench: 18% for GPT-5 and 58% for Qwen3.8 Max.
  • Qwen3.8 Max is cheaper at $2 / $6 per million input/output tokens, against $1.25 / $10 for GPT-5.
  • Qwen3.8 Max accepts more context: 1M tokens versus 400K.

Side by side

GPT-5Qwen3.8 Max
ProviderOpenAIAlibaba (Qwen)
Noometry Index50.956.8
Released2025-08-072026-08-02
WeightsProprietaryProprietary
Context window400K1M
Max output128K131K
Input $ / M tokens$1.25$2
Output $ / M tokens$10$6
Results tracked6939

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

Category by category

Coding Qwen3.8 Max leads

GPT-5: 50.3 (#47), Qwen3.8 Max: 53.5 (#29)

BenchmarkGPT-5Qwen3.8 Max
LMArena WebDev14181674
SciCode42.9%53.2%
LMArena Coding14361502
SWE-bench Verified73.6%—
DeepSWE—57.5%
SWE-bench Verified (bash only)65%—
Aider Polyglot88%—
FrontierSWE—17.8%
GSO6.9%—
WeirdML60.7%—
ALE-Bench1,162—
AlgoTune1.67—

Agentic & Tool Use Qwen3.8 Max leads

GPT-5: 33.1 (#56), Qwen3.8 Max: 45.4 (#14)

BenchmarkGPT-5Qwen3.8 Max
Terminal-Bench49.6%—
APEX-Agents—63.3%
GDPval34.8%—
Remote Labor Index1.7%—
τ²-bench Banking—55.1%
DeepResearch Bench49.6%—
BALROG32.8%—
GDP.pdf—23.2%
LMArena Search1133—
METR Time Horizons69.6%—

Reasoning Qwen3.8 Max leads

GPT-5: 38.3 (#64), Qwen3.8 Max: 54.4 (#26)

BenchmarkGPT-5Qwen3.8 Max
CritPt12.6%20%
Chess Puzzles37%40%
LMArena Hard Prompts14161496
Mystery Game Puzzles23%38%
DTBench90.7%92%
LMCA40%46.2%
Epoch Capabilities Index150156.41
ARC-AGI-29.9%—
SimpleBench56.7%—
Kagi LLM Benchmark72.7%—
NYT Connections (extended)—88.3%
ARC-AGI-165.7%—
EnigmaEval10.5%—
EBR-Bench12.7%—
ForecastBench61.4—

Math Qwen3.8 Max leads

GPT-5: 55.0 (#44), Qwen3.8 Max: 73.2 (#20)

BenchmarkGPT-5Qwen3.8 Max
FrontierMath (Tiers 1-3)55.4%74.7%
FrontierMath Tier 422%46.3%
OTIS Mock AIME 2024-202591.4%100%
ProofBench18%58%
LMArena Math14071499
Omni-MATH64.7%—
MATH Level 598.1%—
FrontierMath (Feb 2025 set)32.4%—
FrontierMath Tier 4 (v1)12.5%—

Knowledge Qwen3.8 Max leads

GPT-5: 56.6 (#43), Qwen3.8 Max: 61.7 (#27)

BenchmarkGPT-5Qwen3.8 Max
GPQA Diamond86.2%92.7%
SimpleQA Verified50.1%47.3%
LMArena Expert14191507
Humanity's Last Exam25.3%—
MMLU-Pro86.3%—
Confabulations10.3%—
Vectara Hallucination Rate14.7%—
GPQA (HELM)79.2%—

Multimodal GPT-5 leads

GPT-5: 46.8 (#13), Qwen3.8 Max: 37.2 (#75)

BenchmarkGPT-5Qwen3.8 Max
LMArena Vision12321314
GeoBench81%—
VPCT66%—
Furniture Assembly—20%

Multilingual Qwen3.8 Max leads

GPT-5: 51.4 (#110), Qwen3.8 Max: 56.7 (#18)

BenchmarkGPT-5Qwen3.8 Max
LMArena Non-English13971472
LMArena Chinese14221538
LMArena French14101503
LMArena German14161483
LMArena Japanese14091467
LMArena Korean13601461
LMArena Russian14061481
LMArena Spanish13991492

Instruction Following Qwen3.8 Max leads

GPT-5: 73.8 (#113), Qwen3.8 Max: 77.6 (#17)

BenchmarkGPT-5Qwen3.8 Max
LMArena Instruction Following13881479
IFEval87.5%—

Long Context GPT-5 leads

GPT-5: 69.5 (#2), Qwen3.8 Max: 45.6 (#31)

BenchmarkGPT-5Qwen3.8 Max
LMArena Longer Query13991489
Fiction.LiveBench97.2%—

Writing & Preference Qwen3.8 Max leads

GPT-5: 63.4 (#65), Qwen3.8 Max: 67.1 (#30)

BenchmarkGPT-5Qwen3.8 Max
LMArena Text14061483
LMArena Creative Writing13651479
LMArena Multi-Turn14261489
Short-Story Creative Writing86%—
EQ-Bench Creative Writing1627—
WildBench85.7%—

Frequently asked questions

Is GPT-5 better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 50.9 on the Noometry Index.

Which is cheaper, GPT-5 or Qwen3.8 Max?

Qwen3.8 Max is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; GPT-5 lists at $1.25 and $10.

Is GPT-5 or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 50.3 in the Noometry coding category.

Which has the bigger context window?

Qwen3.8 Max does, with 1M tokens against 400K.

How many benchmarks do GPT-5 and Qwen3.8 Max share?

32 benchmarks have published results for both models. GPT-5 has 69 scored results on Noometry and Qwen3.8 Max has 39.

Related comparisons

Go deeper