Noometry

Model comparison

Claude 3 Opus vs Qwen3.8 Max

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 29.5 on the Noometry Index.

Last verified . 25 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

Qwen3.8 Max Alibaba (Qwen)

56.8

Rank #22 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and Qwen3.8 Max in 10 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.8 Max leads 73.2 to 14.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 100% for Qwen3.8 Max.

Side by side

Claude 3 OpusQwen3.8 Max
ProviderAnthropicAlibaba (Qwen)
Noometry Index29.556.8
Released2024-02-292026-08-02
WeightsProprietaryProprietary
Context window—1M
Max output—131K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked4639

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

Category by category

Coding Qwen3.8 Max leads

Claude 3 Opus: 32.9 (#267), Qwen3.8 Max: 53.5 (#29)

BenchmarkClaude 3 OpusQwen3.8 Max
LMArena Coding12641502
DeepSWE—57.5%
LMArena WebDev—1674
FrontierSWE—17.8%
SciCode—53.2%
WeirdML19.2%—
BigCodeBench Instruct45.5%—
LiveBench Coding38.6%—
BigCodeBench Complete57.4%—
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use Qwen3.8 Max leads

Claude 3 Opus: 24.6 (#116), Qwen3.8 Max: 45.4 (#14)

BenchmarkClaude 3 OpusQwen3.8 Max
APEX-Agents—63.3%
τ²-bench Banking—55.1%
Cybench10%—
GDP.pdf—23.2%
METR Time Horizons29.5%—

Reasoning Qwen3.8 Max leads

Claude 3 Opus: 14.6 (#324), Qwen3.8 Max: 54.4 (#26)

BenchmarkClaude 3 OpusQwen3.8 Max
Chess Puzzles5%40%
LMArena Hard Prompts12451496
DTBench61.6%92%
LMCA17%46.2%
Epoch Capabilities Index126.91156.41
SimpleBench23.5%—
NYT Connections (extended)—88.3%
CritPt—20%
EnigmaEval0.8%—
LiveBench Reasoning40.6%—
Mystery Game Puzzles—38%
LiveBench Data Analysis57.9%—
ForecastBench58.4—
LiveBench49.2%—
WinoGrande88.5%—

Math Qwen3.8 Max leads

Claude 3 Opus: 14.8 (#299), Qwen3.8 Max: 73.2 (#20)

BenchmarkClaude 3 OpusQwen3.8 Max
OTIS Mock AIME 2024-20254.7%100%
LMArena Math12731499
FrontierMath (Tiers 1-3)—74.7%
FrontierMath Tier 4—46.3%
ProofBench—58%
LiveBench Math43.6%—
MATH Level 537.5%—

Knowledge Qwen3.8 Max leads

Claude 3 Opus: 24.5 (#267), Qwen3.8 Max: 61.7 (#27)

BenchmarkClaude 3 OpusQwen3.8 Max
GPQA Diamond47.2%92.7%
SimpleQA Verified12.6%47.3%
LMArena Expert12231507
Confabulations22.7%—
MMLU84.6%—

Multimodal Qwen3.8 Max leads

Claude 3 Opus: 27.1 (#116), Qwen3.8 Max: 37.2 (#75)

BenchmarkClaude 3 OpusQwen3.8 Max
LMArena Vision10231314
Furniture Assembly—20%

Multilingual Qwen3.8 Max leads

Claude 3 Opus: 41.4 (#207), Qwen3.8 Max: 56.7 (#18)

BenchmarkClaude 3 OpusQwen3.8 Max
LMArena Non-English12581472
LMArena Chinese12481538
LMArena French12751503
LMArena German12581483
LMArena Japanese12041467
LMArena Korean11871461
LMArena Russian12801481
LMArena Spanish12461492

Instruction Following Qwen3.8 Max leads

Claude 3 Opus: 64.1 (#228), Qwen3.8 Max: 77.6 (#17)

BenchmarkClaude 3 OpusQwen3.8 Max
LMArena Instruction Following12481479
LiveBench Instruction Following63.9%—

Long Context Qwen3.8 Max leads

Claude 3 Opus: 38.2 (#202), Qwen3.8 Max: 45.6 (#31)

BenchmarkClaude 3 OpusQwen3.8 Max
LMArena Longer Query12591489

Writing & Preference Qwen3.8 Max leads

Claude 3 Opus: 47.2 (#213), Qwen3.8 Max: 67.1 (#30)

BenchmarkClaude 3 OpusQwen3.8 Max
LMArena Text12621483
LMArena Creative Writing12351479
LMArena Multi-Turn12751489
LiveBench Language50.4%—

Frequently asked questions

Is Claude 3 Opus better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 29.5 on the Noometry Index.

Is Claude 3 Opus or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3 Opus and Qwen3.8 Max share?

25 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Qwen3.8 Max has 39.

Related comparisons

Go deeper