Noometry

Model comparison

Claude 3 Opus vs Qwen3.5 397B-A17B

Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 29.5 on the Noometry Index.

Last verified . 24 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

Qwen3.5 397B-A17B Alibaba (Qwen)

46.0

Rank #67 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and Qwen3.5 397B-A17B in 10 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.5 397B-A17B leads 46.1 to 14.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 88.9% for Qwen3.5 397B-A17B.
  • Qwen3.5 397B-A17B has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusQwen3.5 397B-A17B
ProviderAnthropicAlibaba (Qwen)
Noometry Index29.546.0
Released2024-02-292026-02-01
WeightsProprietaryOpen
Context window—262K
Max output—66K
Input $ / M tokens—$0.60
Output $ / M tokens—$3.60
Results tracked4636

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

Category by category

Coding Qwen3.5 397B-A17B leads

Claude 3 Opus: 32.9 (#267), Qwen3.5 397B-A17B: 42.0 (#114)

BenchmarkClaude 3 OpusQwen3.5 397B-A17B
LMArena Coding12641465
LMArena WebDev—1400
WeirdML19.2%—
BigCodeBench Instruct45.5%—
LiveBench Coding38.6%—
BigCodeBench Complete57.4%—
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use Qwen3.5 397B-A17B leads

Claude 3 Opus: 24.6 (#116), Qwen3.5 397B-A17B: 33.3 (#53)

BenchmarkClaude 3 OpusQwen3.5 397B-A17B
APEX-Agents—24.9%
τ²-bench Airline—81.5%
τ²-bench Banking—9.8%
τ²-bench Retail—84.4%
τ²-bench Telecom—97.8%
Cybench10%—
METR Time Horizons29.5%—

Reasoning Qwen3.5 397B-A17B leads

Claude 3 Opus: 14.6 (#324), Qwen3.5 397B-A17B: 34.5 (#70)

BenchmarkClaude 3 OpusQwen3.5 397B-A17B
Chess Puzzles5%13%
LMArena Hard Prompts12451448
DTBench61.6%87.5%
LMCA17%37.9%
Epoch Capabilities Index126.91146.65
SimpleBench23.5%—
Kagi LLM Benchmark—73.7%
NYT Connections (extended)—58.9%
EnigmaEval0.8%—
Thematic Generalization—65.1%
LiveBench Reasoning40.6%—
Mystery Game Puzzles—18%
LiveBench Data Analysis57.9%—
ForecastBench58.4—
LiveBench49.2%—
WinoGrande88.5%—

Math Qwen3.5 397B-A17B leads

Claude 3 Opus: 14.8 (#299), Qwen3.5 397B-A17B: 46.1 (#73)

BenchmarkClaude 3 OpusQwen3.5 397B-A17B
OTIS Mock AIME 2024-20254.7%88.9%
LMArena Math12731454
FrontierMath (Tiers 1-3)—31.2%
LiveBench Math43.6%—
MATH Level 537.5%—

Knowledge Qwen3.5 397B-A17B leads

Claude 3 Opus: 24.5 (#267), Qwen3.5 397B-A17B: 53.3 (#58)

BenchmarkClaude 3 OpusQwen3.5 397B-A17B
GPQA Diamond47.2%86.4%
LMArena Expert12231462
SimpleQA Verified12.6%—
Confabulations22.7%—
MMLU84.6%—

Multimodal Qwen3.5 397B-A17B leads

Claude 3 Opus: 27.1 (#116), Qwen3.5 397B-A17B: 40.7 (#44)

BenchmarkClaude 3 OpusQwen3.5 397B-A17B
LMArena Vision10231263

Multilingual Qwen3.5 397B-A17B leads

Claude 3 Opus: 41.4 (#207), Qwen3.5 397B-A17B: 53.7 (#59)

BenchmarkClaude 3 OpusQwen3.5 397B-A17B
LMArena Non-English12581430
LMArena Chinese12481500
LMArena French12751461
LMArena German12581447
LMArena Japanese12041426
LMArena Korean11871384
LMArena Russian12801429
LMArena Spanish12461441

Instruction Following Qwen3.5 397B-A17B leads

Claude 3 Opus: 64.1 (#228), Qwen3.5 397B-A17B: 75.0 (#77)

BenchmarkClaude 3 OpusQwen3.5 397B-A17B
LMArena Instruction Following12481424
LiveBench Instruction Following63.9%—

Long Context Qwen3.5 397B-A17B leads

Claude 3 Opus: 38.2 (#202), Qwen3.5 397B-A17B: 44.1 (#74)

BenchmarkClaude 3 OpusQwen3.5 397B-A17B
LMArena Longer Query12591442

Writing & Preference Qwen3.5 397B-A17B leads

Claude 3 Opus: 47.2 (#213), Qwen3.5 397B-A17B: 62.3 (#79)

BenchmarkClaude 3 OpusQwen3.5 397B-A17B
LMArena Text12621438
LMArena Creative Writing12351401
LMArena Multi-Turn12751446
EQ-Bench Creative Writing—1478
LiveBench Language50.4%—

Frequently asked questions

Is Claude 3 Opus better than Qwen3.5 397B-A17B?

Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 29.5 on the Noometry Index.

Is Claude 3 Opus or Qwen3.5 397B-A17B better for coding?

Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3 Opus and Qwen3.5 397B-A17B share?

24 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Qwen3.5 397B-A17B has 36.

Related comparisons

Go deeper