Noometry

Model comparison

Claude Fable 5.1 vs Qwen2-72B

Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 29.5 on the Noometry Index.

Last verified . 18 shared benchmarks.

Claude Fable 5.1 Anthropic

68.5

Rank #2 Confirmed

Qwen2-72B Alibaba (Qwen)

29.5

Rank #294 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Claude Fable 5.1 scores higher in 9 categories and Qwen2-72B in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Fable 5.1 leads 89.5 to 27.9.
  • The biggest single-benchmark swing is WeirdML: 92.9% for Claude Fable 5.1 and 11.3% for Qwen2-72B.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

Claude Fable 5.1Qwen2-72B
ProviderAnthropicAlibaba (Qwen)
Noometry Index68.529.5
Released2026-09-012024-06-07
WeightsProprietaryOpen
Context window1M—
Max output128K—
Input $ / M tokens$10—
Output $ / M tokens$50—
Results tracked5026

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

Category by category

Coding Claude Fable 5.1 leads

Claude Fable 5.1: 70.5 (#2), Qwen2-72B: 28.7 (#303)

BenchmarkClaude Fable 5.1Qwen2-72B
WeirdML92.9%11.3%
LMArena Coding15231196
FrontierCode50.9%—
CursorBench51.8%—
LMArena WebDev1753—
FrontierSWE56.3%—
SciCode63.1%—
BigCodeBench Instruct—38.5%
MirrorCode73.3%—
BigCodeBench Complete—54%
ALE-Bench2,143—

Agentic & Tool Use Claude Fable 5.1 leads

Claude Fable 5.1: 50.8 (#5), Qwen2-72B: 16.9 (#138)

BenchmarkClaude Fable 5.1Qwen2-72B
APEX-Agents68.6%—
Remote Labor Index17.9%—
TheAgentCompany—1.1%
GDP.pdf29.6%—
METR Time Horizons—29.9%
Vending-Bench 25,422—

Reasoning Claude Fable 5.1 leads

Claude Fable 5.1: 76.7 (#5), Qwen2-72B: 22.2 (#184)

BenchmarkClaude Fable 5.1Qwen2-72B
LMArena Hard Prompts15261191
Epoch Capabilities Index165125.27
ARC-AGI-290%—
NYT Connections (extended)90%—
ARC-AGI-197.5%—
CritPt31.1%—
Chess Puzzles47%—
EBR-Bench57.1%—
Mystery Game Puzzles58%—
DTBench97.6%—
LMCA65.5%—

Math Claude Fable 5.1 leads

Claude Fable 5.1: 89.5 (#3), Qwen2-72B: 27.9 (#232)

BenchmarkClaude Fable 5.1Qwen2-72B
LMArena Math15191235
FrontierMath (Tiers 1-3)90.2%—
FrontierMath Tier 487.8%—
OTIS Mock AIME 2024-2025100%—
ProofBench100%—
MATH Level 5—39.1%
FrontierMath Erdős0%—

Knowledge Claude Fable 5.1 leads

Claude Fable 5.1: 69.3 (#5), Qwen2-72B: 21.2 (#270)

BenchmarkClaude Fable 5.1Qwen2-72B
LMArena Expert15281171
GPQA Diamond—40.8%
Humanity's Last Exam46.5%—
SimpleQA Verified70.8%—
MMLU—82.4%

Multimodal Not comparable

Claude Fable 5.1: 54.1 (#4), Qwen2-72B: —

BenchmarkClaude Fable 5.1Qwen2-72B
LMArena Vision1319—
Blueprint-Bench 241.9%—
Furniture Assembly70%—
LMArena Document1513—

Multilingual Claude Fable 5.1 leads

Claude Fable 5.1: 59.5 (#2), Qwen2-72B: 36.0 (#239)

BenchmarkClaude Fable 5.1Qwen2-72B
LMArena Non-English15091176
LMArena Chinese15891240
LMArena French15321169
LMArena German14951151
LMArena Japanese15651111
LMArena Russian15251169
LMArena Spanish15031168
LMArena Korean—1083

Instruction Following Claude Fable 5.1 leads

Claude Fable 5.1: 79.3 (#6), Qwen2-72B: 62.0 (#236)

BenchmarkClaude Fable 5.1Qwen2-72B
LMArena Instruction Following15151181

Long Context Claude Fable 5.1 leads

Claude Fable 5.1: 46.8 (#19), Qwen2-72B: 36.1 (#230)

BenchmarkClaude Fable 5.1Qwen2-72B
LMArena Longer Query15241193

Writing & Preference Claude Fable 5.1 leads

Claude Fable 5.1: 79.3 (#1), Qwen2-72B: 41.0 (#236)

BenchmarkClaude Fable 5.1Qwen2-72B
LMArena Text15111203
LMArena Creative Writing15071181
LMArena Multi-Turn14921195
EQ-Bench Creative Writing2162—

Frequently asked questions

Is Claude Fable 5.1 better than Qwen2-72B?

Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 29.5 on the Noometry Index.

Is Claude Fable 5.1 or Qwen2-72B better for coding?

Claude Fable 5.1 scores higher on coding benchmarks: 70.5 versus 28.7 in the Noometry coding category.

How many benchmarks do Claude Fable 5.1 and Qwen2-72B share?

18 benchmarks have published results for both models. Claude Fable 5.1 has 50 scored results on Noometry and Qwen2-72B has 26.

Related comparisons

Go deeper