Noometry

Model comparison

Claude Fable 5.1 vs Qwen3-4B

Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 31.9 on the Noometry Index.

Last verified . 2 shared benchmarks.

Claude Fable 5.1 Anthropic

69.0

Rank #2 Confirmed

Qwen3-4B Alibaba (Qwen)

31.9

Rank #264 Confirmed

Summary

  • They share 2 benchmarks with published results for both. Claude Fable 5.1 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 Fable 5.1 leads 89.6 to 29.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 100% for Claude Fable 5.1 and 52.2% for Qwen3-4B.
  • Qwen3-4B has downloadable open weights; the other is API-only.

Side by side

Claude Fable 5.1Qwen3-4B
ProviderAnthropicAlibaba (Qwen)
Noometry Index69.031.9
Released2026-09-012025-04-29
WeightsProprietaryOpen
Context window1M—
Max output128K—
Input $ / M tokens$10—
Output $ / M tokens$50—
Results tracked526

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

Category by category

Coding Not comparable

Claude Fable 5.1: 74.7 (#1), Qwen3-4B: —

BenchmarkClaude Fable 5.1Qwen3-4B
FrontierCode50.9%—
CursorBench51.8%—
LMArena WebDev1744—
FrontierSWE56.3%—
SciCode63.1%—
GSO88.2%—
WeirdML92.9%—
LMArena Coding1528—
MirrorCode73.3%—
ALE-Bench2,143—

Agentic & Tool Use Claude Fable 5.1 leads

Claude Fable 5.1: 50.7 (#5), Qwen3-4B: 27.6 (#100)

BenchmarkClaude Fable 5.1Qwen3-4B
APEX-Agents68.6%—
Berkeley Function Calling Leaderboard—35.7%
Remote Labor Index17.9%—
GDP.pdf29.6%—
Vending-Bench 25,422—

Reasoning Claude Fable 5.1 leads

Claude Fable 5.1: 76.7 (#7), Qwen3-4B: 19.2 (#268)

BenchmarkClaude Fable 5.1Qwen3-4B
Chess Puzzles47%4%
ARC-AGI-290%—
NYT Connections (extended)90%—
ARC-AGI-197.5%—
CritPt31.1%—
EBR-Bench57.1%—
LMArena Hard Prompts1526—
Mystery Game Puzzles58%—
DTBench97.6%—
LMCA65.5%—
Epoch Capabilities Index164.7—

Math Claude Fable 5.1 leads

Claude Fable 5.1: 89.6 (#4), Qwen3-4B: 29.7 (#240)

BenchmarkClaude Fable 5.1Qwen3-4B
OTIS Mock AIME 2024-2025100%52.2%
FrontierMath (Tiers 1-3)90.2%—
FrontierMath Tier 487.8%—
MathArena Final-Answer Competitions—38.5%
ProofBench100%—
LMArena Math1525—
FrontierMath Erdős0%—

Knowledge Claude Fable 5.1 leads

Claude Fable 5.1: 69.6 (#6), Qwen3-4B: 33.0 (#208)

BenchmarkClaude Fable 5.1Qwen3-4B
GPQA Diamond—52.3%
Humanity's Last Exam46.5%—
SimpleQA Verified70.8%—
Vectara Hallucination Rate—5.7%
LMArena Expert1535—

Multimodal Not comparable

Claude Fable 5.1: 53.9 (#4), Qwen3-4B: —

BenchmarkClaude Fable 5.1Qwen3-4B
LMArena Vision1318—
Blueprint-Bench 241.9%—
Furniture Assembly70%—
LMArena Document1513—

Multilingual Not comparable

Claude Fable 5.1: 59.1 (#3), Qwen3-4B: —

BenchmarkClaude Fable 5.1Qwen3-4B
LMArena Non-English1507—
LMArena Chinese1586—
LMArena French1525—
LMArena German1500—
LMArena Japanese1543—
LMArena Korean1534—
LMArena Russian1521—
LMArena Spanish1516—

Instruction Following Not comparable

Claude Fable 5.1: 79.2 (#6), Qwen3-4B: —

BenchmarkClaude Fable 5.1Qwen3-4B
LMArena Instruction Following1517—

Long Context Not comparable

Claude Fable 5.1: 46.7 (#20), Qwen3-4B: —

BenchmarkClaude Fable 5.1Qwen3-4B
LMArena Longer Query1522—

Writing & Preference Not comparable

Claude Fable 5.1: 79.2 (#2), Qwen3-4B: —

BenchmarkClaude Fable 5.1Qwen3-4B
LMArena Text1510—
LMArena Creative Writing1507—
EQ-Bench Creative Writing2162—
LMArena Multi-Turn1492—

Frequently asked questions

Is Claude Fable 5.1 better than Qwen3-4B?

Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 31.9 on the Noometry Index.

How many benchmarks do Claude Fable 5.1 and Qwen3-4B share?

2 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and Qwen3-4B has 6.

Related comparisons

Go deeper