Noometry

Model comparison

Qwen3.8 Max vs Step 2 16k Exp 202412

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 39.2 on the Noometry Index.

Last verified . 12 shared benchmarks.

Qwen3.8 Max Alibaba (Qwen)

56.8

Rank #22 Confirmed

Step 2 16k Exp 202412 StepFun

39.2

Rank #171 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Qwen3.8 Max scores higher in 8 categories and Step 2 16k Exp 202412 in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.8 Max leads 73.2 to 36.3.

Side by side

Qwen3.8 MaxStep 2 16k Exp 202412
ProviderAlibaba (Qwen)StepFun
Noometry Index56.839.2
Released2026-08-02—
WeightsProprietaryProprietary
Context window1M—
Max output131K—
Input $ / M tokens$2—
Output $ / M tokens$6—
Results tracked3912

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

Category by category

Coding Qwen3.8 Max leads

Qwen3.8 Max: 53.5 (#29), Step 2 16k Exp 202412: 38.5 (#174)

BenchmarkQwen3.8 MaxStep 2 16k Exp 202412
LMArena Coding15021316
DeepSWE57.5%—
LMArena WebDev1674—
FrontierSWE17.8%—
SciCode53.2%—

Agentic & Tool Use Not comparable

Qwen3.8 Max: 45.4 (#14), Step 2 16k Exp 202412: —

BenchmarkQwen3.8 MaxStep 2 16k Exp 202412
APEX-Agents63.3%—
τ²-bench Banking55.1%—
GDP.pdf23.2%—

Reasoning Qwen3.8 Max leads

Qwen3.8 Max: 54.4 (#26), Step 2 16k Exp 202412: 25.9 (#142)

BenchmarkQwen3.8 MaxStep 2 16k Exp 202412
LMArena Hard Prompts14961299
NYT Connections (extended)88.3%—
CritPt20%—
Chess Puzzles40%—
Mystery Game Puzzles38%—
DTBench92%—
LMCA46.2%—
Epoch Capabilities Index156.41—

Math Qwen3.8 Max leads

Qwen3.8 Max: 73.2 (#20), Step 2 16k Exp 202412: 36.3 (#169)

BenchmarkQwen3.8 MaxStep 2 16k Exp 202412
LMArena Math14991304
FrontierMath (Tiers 1-3)74.7%—
FrontierMath Tier 446.3%—
OTIS Mock AIME 2024-2025100%—
ProofBench58%—

Knowledge Qwen3.8 Max leads

Qwen3.8 Max: 61.7 (#27), Step 2 16k Exp 202412: 35.2 (#187)

BenchmarkQwen3.8 MaxStep 2 16k Exp 202412
LMArena Expert15071279
GPQA Diamond92.7%—
SimpleQA Verified47.3%—

Multimodal Not comparable

Qwen3.8 Max: 37.2 (#75), Step 2 16k Exp 202412: —

BenchmarkQwen3.8 MaxStep 2 16k Exp 202412
LMArena Vision1314—
Furniture Assembly20%—

Multilingual Qwen3.8 Max leads

Qwen3.8 Max: 56.7 (#18), Step 2 16k Exp 202412: 43.7 (#181)

BenchmarkQwen3.8 MaxStep 2 16k Exp 202412
LMArena Non-English14721290
LMArena Chinese15381331
LMArena Russian14811324
LMArena French1503—
LMArena German1483—
LMArena Japanese1467—
LMArena Korean1461—
LMArena Spanish1492—

Instruction Following Qwen3.8 Max leads

Qwen3.8 Max: 77.6 (#17), Step 2 16k Exp 202412: 67.9 (#192)

BenchmarkQwen3.8 MaxStep 2 16k Exp 202412
LMArena Instruction Following14791287

Long Context Qwen3.8 Max leads

Qwen3.8 Max: 45.6 (#31), Step 2 16k Exp 202412: 39.7 (#170)

BenchmarkQwen3.8 MaxStep 2 16k Exp 202412
LMArena Longer Query14891307

Writing & Preference Qwen3.8 Max leads

Qwen3.8 Max: 67.1 (#30), Step 2 16k Exp 202412: 52.3 (#173)

BenchmarkQwen3.8 MaxStep 2 16k Exp 202412
LMArena Text14831321
LMArena Creative Writing14791328
LMArena Multi-Turn14891292

Frequently asked questions

Is Qwen3.8 Max better than Step 2 16k Exp 202412?

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 39.2 on the Noometry Index.

Is Qwen3.8 Max or Step 2 16k Exp 202412 better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 38.5 in the Noometry coding category.

How many benchmarks do Qwen3.8 Max and Step 2 16k Exp 202412 share?

12 benchmarks have published results for both models. Qwen3.8 Max has 39 scored results on Noometry and Step 2 16k Exp 202412 has 12.

Related comparisons

Go deeper