Noometry

Model comparison

Claude Opus 4.8 vs Qwen3-4B

Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 31.5 on the Noometry Index.

Last verified . 4 shared benchmarks.

Claude Opus 4.8 Anthropic

60.7

Rank #9 Confirmed

Qwen3-4B Alibaba (Qwen)

31.5

Rank #261 Confirmed

Summary

  • They share 4 benchmarks with published results for both. Claude Opus 4.8 scores higher in 4 categories and Qwen3-4B in 0 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Opus 4.8 leads 78.2 to 28.5.
  • The biggest single-benchmark swing is MathArena Final-Answer Competitions: 91.8% for Claude Opus 4.8 and 38.5% for Qwen3-4B.
  • Qwen3-4B has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.8Qwen3-4B
ProviderAnthropicAlibaba (Qwen)
Noometry Index60.731.5
Released2026-05-282025-04-29
WeightsProprietaryOpen
Context window1M—
Max output128K—
Input $ / M tokens$5—
Output $ / M tokens$25—
Results tracked656

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

Category by category

Coding Not comparable

Claude Opus 4.8: 60.2 (#9), Qwen3-4B: —

BenchmarkClaude Opus 4.8Qwen3-4B
DeepSWE59%—
FrontierCode46.5%—
LMArena WebDev1556—
SciCode53.5%—
GSO47.1%—
WeirdML82.9%—
LMArena Coding1491—
ALE-Bench1,564—

Agentic & Tool Use Claude Opus 4.8 leads

Claude Opus 4.8: 47.6 (#10), Qwen3-4B: 27.3 (#94)

BenchmarkClaude Opus 4.8Qwen3-4B
APEX-Agents48.9%—
Berkeley Function Calling Leaderboard—35.7%
OSWorld 2.020.6%—
Remote Labor Index8.3%—
τ²-bench Banking39.7%—
DeepResearch Bench50.2%—
PostTrainBench33.8%—
GBAEval70.9%—
GDP.pdf24%—
LMArena Search1204—
Vending-Bench 25,787—

Reasoning Claude Opus 4.8 leads

Claude Opus 4.8: 64.6 (#14), Qwen3-4B: 18.5 (#264)

BenchmarkClaude Opus 4.8Qwen3-4B
Chess Puzzles34%4%
ARC-AGI-272.1%—
SimpleBench64.8%—
Kagi LLM Benchmark88.8%—
NYT Connections (extended)91.1%—
ARC-AGI-192.5%—
CritPt20.9%—
EnigmaEval23.5%—
EBR-Bench28.6%—
LMArena Hard Prompts1481—
Mystery Game Puzzles36%—
DTBench94.9%—
LMCA57.5%—
Surface Evolver Bench87.5%—
Bench to the Future 30.14—
Epoch Capabilities Index158.3—
ForecastBench59.9—

Math Claude Opus 4.8 leads

Claude Opus 4.8: 78.2 (#11), Qwen3-4B: 28.5 (#228)

BenchmarkClaude Opus 4.8Qwen3-4B
MathArena Final-Answer Competitions91.8%38.5%
OTIS Mock AIME 2024-202598.3%52.2%
FrontierMath (Tiers 1-3)80%—
FrontierMath Tier 456.1%—
ProofBench69%—
LMArena Math1487—
FrontierMath (Feb 2025 set)47.2%—
FrontierMath Tier 4 (v1)31.3%—

Knowledge Claude Opus 4.8 leads

Claude Opus 4.8: 61.3 (#26), Qwen3-4B: 33.0 (#198)

BenchmarkClaude Opus 4.8Qwen3-4B
GPQA Diamond91%52.3%
SimpleQA Verified53%—
Vectara Hallucination Rate—5.7%
LMArena Expert1501—

Multimodal Not comparable

Claude Opus 4.8: 43.2 (#20), Qwen3-4B: —

BenchmarkClaude Opus 4.8Qwen3-4B
LMArena Vision1295—
Blueprint-Bench 214.5%—
Furniture Assembly42.5%—
LMArena Document1475—

Multilingual Not comparable

Claude Opus 4.8: 55.4 (#31), Qwen3-4B: —

BenchmarkClaude Opus 4.8Qwen3-4B
LMArena Non-English1450—
LMArena Chinese1509—
LMArena French1482—
LMArena German1470—
LMArena Japanese1440—
LMArena Korean1432—
LMArena Russian1476—
LMArena Spanish1470—

Instruction Following Not comparable

Claude Opus 4.8: 77.6 (#22), Qwen3-4B: —

BenchmarkClaude Opus 4.8Qwen3-4B
LMArena Instruction Following1476—

Long Context Not comparable

Claude Opus 4.8: 45.4 (#37), Qwen3-4B: —

BenchmarkClaude Opus 4.8Qwen3-4B
LMArena Longer Query1482—

Writing & Preference Not comparable

Claude Opus 4.8: 72.1 (#17), Qwen3-4B: —

BenchmarkClaude Opus 4.8Qwen3-4B
LMArena Text1460—
LMArena Creative Writing1453—
EQ-Bench Creative Writing1840—
EQ-Bench 41281—
LMArena Multi-Turn1476—

Frequently asked questions

Is Claude Opus 4.8 better than Qwen3-4B?

Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 31.5 on the Noometry Index.

How many benchmarks do Claude Opus 4.8 and Qwen3-4B share?

4 benchmarks have published results for both models. Claude Opus 4.8 has 65 scored results on Noometry and Qwen3-4B has 6.

Related comparisons

Go deeper