Noometry

Model comparison

Grok-2 (Dec 2024) vs Qwen3.8 Max

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 33.7 on the Noometry Index.

Last verified . 21 shared benchmarks.

Grok-2 (Dec 2024) xAI

33.7

Rank #239 Confirmed

Qwen3.8 Max Alibaba (Qwen)

56.8

Rank #22 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 0 categories and Qwen3.8 Max in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.8 Max leads 73.2 to 20.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 11.5% for Grok-2 (Dec 2024) and 100% for Qwen3.8 Max.

Side by side

Grok-2 (Dec 2024)Qwen3.8 Max
ProviderxAIAlibaba (Qwen)
Noometry Index33.756.8
Released2024-08-132026-08-02
WeightsProprietaryProprietary
Context window—1M
Max output—131K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked3439

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

Category by category

Coding Qwen3.8 Max leads

Grok-2 (Dec 2024): 33.3 (#258), Qwen3.8 Max: 53.5 (#29)

BenchmarkGrok-2 (Dec 2024)Qwen3.8 Max
LMArena Coding12871502
DeepSWE—57.5%
LMArena WebDev—1674
FrontierSWE—17.8%
SciCode—53.2%
WeirdML22.2%—
LiveBench Coding46.4%—

Agentic & Tool Use Not comparable

Grok-2 (Dec 2024): —, Qwen3.8 Max: 45.4 (#14)

BenchmarkGrok-2 (Dec 2024)Qwen3.8 Max
APEX-Agents—63.3%
τ²-bench Banking—55.1%
GDP.pdf—23.2%

Reasoning Qwen3.8 Max leads

Grok-2 (Dec 2024): 16.9 (#299), Qwen3.8 Max: 54.4 (#26)

BenchmarkGrok-2 (Dec 2024)Qwen3.8 Max
LMArena Hard Prompts12721496
DTBench65.2%92%
Epoch Capabilities Index130.48156.41
SimpleBench22.7%—
NYT Connections (extended)—88.3%
CritPt—20%
Chess Puzzles—40%
LiveBench Reasoning54.8%—
Mystery Game Puzzles—38%
LiveBench Data Analysis54.5%—
LMCA—46.2%
LiveBench54.3%—

Math Qwen3.8 Max leads

Grok-2 (Dec 2024): 20.8 (#284), Qwen3.8 Max: 73.2 (#20)

BenchmarkGrok-2 (Dec 2024)Qwen3.8 Max
OTIS Mock AIME 2024-202511.5%100%
LMArena Math12831499
FrontierMath (Tiers 1-3)—74.7%
FrontierMath Tier 4—46.3%
ProofBench—58%
LiveBench Math54.9%—
MATH Level 563.5%—
FrontierMath (Feb 2025 set)0.7%—

Knowledge Qwen3.8 Max leads

Grok-2 (Dec 2024): 29.8 (#233), Qwen3.8 Max: 61.7 (#27)

BenchmarkGrok-2 (Dec 2024)Qwen3.8 Max
GPQA Diamond53.8%92.7%
LMArena Expert12541507
SimpleQA Verified—47.3%
Confabulations20.1%—

Multimodal Not comparable

Grok-2 (Dec 2024): —, Qwen3.8 Max: 37.2 (#75)

BenchmarkGrok-2 (Dec 2024)Qwen3.8 Max
LMArena Vision—1314
Furniture Assembly—20%

Multilingual Qwen3.8 Max leads

Grok-2 (Dec 2024): 43.1 (#188), Qwen3.8 Max: 56.7 (#18)

BenchmarkGrok-2 (Dec 2024)Qwen3.8 Max
LMArena Non-English12821472
LMArena Chinese12891538
LMArena French13181503
LMArena German12871483
LMArena Japanese12441467
LMArena Korean12371461
LMArena Russian12861481
LMArena Spanish12811492

Instruction Following Qwen3.8 Max leads

Grok-2 (Dec 2024): 66.9 (#202), Qwen3.8 Max: 77.6 (#17)

BenchmarkGrok-2 (Dec 2024)Qwen3.8 Max
LMArena Instruction Following12701479
LiveBench Instruction Following69.6%—

Long Context Qwen3.8 Max leads

Grok-2 (Dec 2024): 38.8 (#190), Qwen3.8 Max: 45.6 (#31)

BenchmarkGrok-2 (Dec 2024)Qwen3.8 Max
LMArena Longer Query12761489

Writing & Preference Qwen3.8 Max leads

Grok-2 (Dec 2024): 48.6 (#198), Qwen3.8 Max: 67.1 (#30)

BenchmarkGrok-2 (Dec 2024)Qwen3.8 Max
LMArena Text13051483
LMArena Creative Writing12841479
LMArena Multi-Turn12901489
Short-Story Creative Writing63.6%—
LiveBench Language45.6%—

Frequently asked questions

Is Grok-2 (Dec 2024) better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 33.7 on the Noometry Index.

Is Grok-2 (Dec 2024) or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 33.3 in the Noometry coding category.

How many benchmarks do Grok-2 (Dec 2024) and Qwen3.8 Max share?

21 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Qwen3.8 Max has 39.

Related comparisons

Go deeper