Noometry

Model comparison

Claude Sonnet 4.6 vs Yi-34B

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 27.8 on the Noometry Index.

Last verified . 19 shared benchmarks.

Claude Sonnet 4.6 Anthropic

50.3

Rank #50 Confirmed

Yi-34B 01.AI

27.8

Rank #329 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 8 categories and Yi-34B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Claude Sonnet 4.6 leads 51.7 to 7.5.
  • The biggest single-benchmark swing is GPQA Diamond: 87.4% for Claude Sonnet 4.6 and 14.7% for Yi-34B.
  • Yi-34B has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.6Yi-34B
ProviderAnthropic01.AI
Noometry Index50.327.8
Released2026-02-172023-11-02
WeightsProprietaryOpen
Context window1M—
Max output128K—
Input $ / M tokens$3—
Output $ / M tokens$15—
Results tracked5723

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

Category by category

Coding Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.3 (#67), Yi-34B: 32.3 (#274)

BenchmarkClaude Sonnet 4.6Yi-34B
LMArena Coding15041112
SWE-bench Verified75.2%—
DeepSWE29.9%—
FrontierCode24.3%—
LMArena WebDev1522—
SciCode46.8%—
WeirdML66.1%—
ALE-Bench1,327—

Agentic & Tool Use Not comparable

Claude Sonnet 4.6: 39.1 (#28), Yi-34B: —

BenchmarkClaude Sonnet 4.6Yi-34B
Terminal-Bench53.4%—
APEX-Agents43%—
OSWorld 2.09.3%—
DeepResearch Bench54.9%—
OSWorld72.1%—
ExploitBench23.6%—
GBAEval48.8%—
GDP.pdf18%—
LMArena Search1221—
Vending-Bench 27,204—

Reasoning Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.1 (#45), Yi-34B: 21.2 (#226)

BenchmarkClaude Sonnet 4.6Yi-34B
LMArena Hard Prompts14841104
Epoch Capabilities Index152.24117.39
ARC-AGI-260.4%—
NYT Connections (extended)80.9%—
ARC-AGI-186.5%—
CritPt3.1%—
Chess Puzzles13%—
Thematic Generalization76.3%—
Mystery Game Puzzles16%—
DTBench89.9%—
LMCA46.5%—
BIG-Bench Hard—71.7%
ForecastBench62—

Math Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 52.9 (#49), Yi-34B: 21.6 (#282)

BenchmarkClaude Sonnet 4.6Yi-34B
LMArena Math14621114
OTIS Mock AIME 2024-202585.8%—
ProofBench45%—
MATH Level 5—5.1%
FrontierMath (Feb 2025 set)32.4%—
FrontierMath Tier 4 (v1)8.3%—
GSM8K—76%

Knowledge Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 51.7 (#65), Yi-34B: 7.5 (#309)

BenchmarkClaude Sonnet 4.6Yi-34B
GPQA Diamond87.4%14.7%
LMArena Expert15001061
SimpleQA Verified35.5%—
Vectara Hallucination Rate10.6%—
MMLU—76.3%

Multimodal Not comparable

Claude Sonnet 4.6: 38.0 (#68), Yi-34B: —

BenchmarkClaude Sonnet 4.6Yi-34B
LMArena Vision1283—
Blueprint-Bench 26.7%—
LMArena Document1482—

Multilingual Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 54.4 (#41), Yi-34B: 29.7 (#264)

BenchmarkClaude Sonnet 4.6Yi-34B
LMArena Non-English14401079
LMArena Chinese14911176
LMArena French14651081
LMArena German14281042
LMArena Japanese1420993
LMArena Korean1411959
LMArena Russian14401050
LMArena Spanish14641070

Instruction Following Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 77.4 (#25), Yi-34B: 56.2 (#274)

BenchmarkClaude Sonnet 4.6Yi-34B
LMArena Instruction Following14751091

Long Context Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 45.3 (#44), Yi-34B: 33.2 (#264)

BenchmarkClaude Sonnet 4.6Yi-34B
LMArena Longer Query14791094

Writing & Preference Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 70.2 (#22), Yi-34B: 34.1 (#273)

BenchmarkClaude Sonnet 4.6Yi-34B
LMArena Text14581129
LMArena Creative Writing14351108
LMArena Multi-Turn14641113
EQ-Bench Creative Writing1810—
EQ-Bench 41207—

Frequently asked questions

Is Claude Sonnet 4.6 better than Yi-34B?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 27.8 on the Noometry Index.

Is Claude Sonnet 4.6 or Yi-34B better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 32.3 in the Noometry coding category.

How many benchmarks do Claude Sonnet 4.6 and Yi-34B share?

19 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Yi-34B has 23.

Related comparisons

Go deeper