Noometry

Model comparison

Claude 3 Opus vs Qwen-14B

Qwen-14B is the stronger model overall, scoring 31.4 to 29.5 on the Noometry Index.

Last verified . 12 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

Qwen-14B Alibaba (Qwen)

31.4

Rank #275 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Claude 3 Opus scores higher in 5 categories and Qwen-14B in 2 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Claude 3 Opus leads 47.2 to 27.6.
  • Qwen-14B has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusQwen-14B
ProviderAnthropicAlibaba (Qwen)
Noometry Index29.531.4
Released2024-02-292023-09-24
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4618

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

Category by category

Coding Claude 3 Opus leads

Claude 3 Opus: 32.9 (#267), Qwen-14B: 31.2 (#288)

BenchmarkClaude 3 OpusQwen-14B
LMArena Coding12641071
WeirdML19.2%—
BigCodeBench Instruct45.5%—
LiveBench Coding38.6%—
BigCodeBench Complete57.4%—
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

Claude 3 Opus: 24.6 (#116), Qwen-14B: —

BenchmarkClaude 3 OpusQwen-14B
Cybench10%—
METR Time Horizons29.5%—

Reasoning Qwen-14B leads

Claude 3 Opus: 14.6 (#324), Qwen-14B: 19.6 (#257)

BenchmarkClaude 3 OpusQwen-14B
LMArena Hard Prompts12451027
Epoch Capabilities Index126.91113.03
SimpleBench23.5%—
Chess Puzzles5%—
EnigmaEval0.8%—
LiveBench Reasoning40.6%—
DTBench61.6%—
LiveBench Data Analysis57.9%—
LMCA17%—
BIG-Bench Hard—55%
ForecastBench58.4—
LAMBADA—71.1%
LiveBench49.2%—
PIQA—79.9%
WinoGrande88.5%—

Math Qwen-14B leads

Claude 3 Opus: 14.8 (#299), Qwen-14B: 31.2 (#227)

BenchmarkClaude 3 OpusQwen-14B
LMArena Math12731068
OTIS Mock AIME 2024-20254.7%—
LiveBench Math43.6%—
MATH Level 537.5%—
GSM8K—61.3%

Knowledge Not comparable

Claude 3 Opus: 24.5 (#267), Qwen-14B: —

BenchmarkClaude 3 OpusQwen-14B
MMLU84.6%66.3%
GPQA Diamond47.2%—
SimpleQA Verified12.6%—
Confabulations22.7%—
LMArena Expert1223—
ARC (AI2) Challenge—84.4%
BoolQ—86.2%

Multimodal Not comparable

Claude 3 Opus: 27.1 (#116), Qwen-14B: —

BenchmarkClaude 3 OpusQwen-14B
LMArena Vision1023—

Multilingual Claude 3 Opus leads

Claude 3 Opus: 41.4 (#207), Qwen-14B: 27.5 (#275)

BenchmarkClaude 3 OpusQwen-14B
LMArena Non-English12581041
LMArena Chinese12481077
LMArena French1275—
LMArena German1258—
LMArena Japanese1204—
LMArena Korean1187—
LMArena Russian1280—
LMArena Spanish1246—

Instruction Following Claude 3 Opus leads

Claude 3 Opus: 64.1 (#228), Qwen-14B: 52.4 (#289)

BenchmarkClaude 3 OpusQwen-14B
LMArena Instruction Following12481031
LiveBench Instruction Following63.9%—

Long Context Claude 3 Opus leads

Claude 3 Opus: 38.2 (#202), Qwen-14B: 31.3 (#280)

BenchmarkClaude 3 OpusQwen-14B
LMArena Longer Query12591028

Writing & Preference Claude 3 Opus leads

Claude 3 Opus: 47.2 (#213), Qwen-14B: 27.6 (#299)

BenchmarkClaude 3 OpusQwen-14B
LMArena Text12621051
LMArena Creative Writing12351028
LMArena Multi-Turn12751022
LiveBench Language50.4%—

Frequently asked questions

Is Claude 3 Opus better than Qwen-14B?

Qwen-14B is the stronger model overall, scoring 31.4 to 29.5 on the Noometry Index.

Is Claude 3 Opus or Qwen-14B better for coding?

Claude 3 Opus scores higher on coding benchmarks: 32.9 versus 31.2 in the Noometry coding category.

How many benchmarks do Claude 3 Opus and Qwen-14B share?

12 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Qwen-14B has 18.

Related comparisons

Go deeper