Noometry

Model comparison

Claude Opus 5 vs Yi-34B

Claude Opus 5 is the stronger model overall, scoring 67.8 to 27.8 on the Noometry Index.

Last verified . 19 shared benchmarks.

Claude Opus 5 Anthropic

67.8

Rank #4 Confirmed

Yi-34B 01.AI

27.8

Rank #329 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Claude Opus 5 scores higher in 8 categories and Yi-34B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Opus 5 leads 86.2 to 21.6.
  • The biggest single-benchmark swing is GPQA Diamond: 93.9% for Claude Opus 5 and 14.7% for Yi-34B.
  • Yi-34B has downloadable open weights; the other is API-only.

Side by side

Claude Opus 5Yi-34B
ProviderAnthropic01.AI
Noometry Index67.827.8
Released2026-07-242023-11-02
WeightsProprietaryOpen
Context window1M—
Max output128K—
Input $ / M tokens$5—
Output $ / M tokens$25—
Results tracked5723

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

Category by category

Coding Claude Opus 5 leads

Claude Opus 5: 67.5 (#5), Yi-34B: 32.3 (#274)

BenchmarkClaude Opus 5Yi-34B
LMArena Coding15341112
DeepSWE73.6%—
FrontierCode53.4%—
CursorBench46.6%—
LMArena WebDev1691—
FrontierSWE52%—
SciCode56.4%—
WeirdML91.8%—
ALE-Bench2,165—

Agentic & Tool Use Not comparable

Claude Opus 5: 55.6 (#1), Yi-34B: —

BenchmarkClaude Opus 5Yi-34B
APEX-Agents65.8%—
OSWorld 2.031.4%—
τ²-bench Banking48.7%—
PostTrainBench35%—
BALROG63.4%—
GBAEval79.6%—
GDP.pdf24%—
Vending-Bench 211,182—

Reasoning Claude Opus 5 leads

Claude Opus 5: 77.2 (#4), Yi-34B: 21.2 (#226)

BenchmarkClaude Opus 5Yi-34B
LMArena Hard Prompts15261104
Epoch Capabilities Index162.78117.39
ARC-AGI-290.4%—
SimpleBench80.6%—
NYT Connections (extended)94.3%—
ARC-AGI-197.5%—
CritPt29.1%—
Chess Puzzles42%—
EBR-Bench45.7%—
Mystery Game Puzzles59%—
DTBench97.9%—
LMCA64.5%—
Bench to the Future 30.12—
BIG-Bench Hard—71.7%

Math Claude Opus 5 leads

Claude Opus 5: 86.2 (#8), Yi-34B: 21.6 (#282)

BenchmarkClaude Opus 5Yi-34B
LMArena Math15311114
FrontierMath (Tiers 1-3)85.6%—
FrontierMath Tier 473.2%—
OTIS Mock AIME 2024-202598.9%—
ProofBench99%—
MATH Level 5—5.1%
GSM8K—76%

Knowledge Claude Opus 5 leads

Claude Opus 5: 66.8 (#9), Yi-34B: 7.5 (#309)

BenchmarkClaude Opus 5Yi-34B
GPQA Diamond93.9%14.7%
LMArena Expert15571061
SimpleQA Verified59.9%—
MMLU—76.3%

Multimodal Not comparable

Claude Opus 5: 50.8 (#8), Yi-34B: —

BenchmarkClaude Opus 5Yi-34B
LMArena Vision1319—
Blueprint-Bench 230.4%—
Furniture Assembly60.8%—
LMArena Document1516—

Multilingual Claude Opus 5 leads

Claude Opus 5: 58.8 (#4), Yi-34B: 29.7 (#264)

BenchmarkClaude Opus 5Yi-34B
LMArena Non-English15011079
LMArena Chinese15741176
LMArena French15191081
LMArena German15241042
LMArena Japanese1516993
LMArena Korean1521959
LMArena Russian15071050
LMArena Spanish15191070

Instruction Following Claude Opus 5 leads

Claude Opus 5: 79.2 (#7), Yi-34B: 56.2 (#274)

BenchmarkClaude Opus 5Yi-34B
LMArena Instruction Following15171091

Long Context Claude Opus 5 leads

Claude Opus 5: 46.5 (#21), Yi-34B: 33.2 (#264)

BenchmarkClaude Opus 5Yi-34B
LMArena Longer Query15151094

Writing & Preference Claude Opus 5 leads

Claude Opus 5: 79.2 (#1), Yi-34B: 34.1 (#273)

BenchmarkClaude Opus 5Yi-34B
LMArena Text15071129
LMArena Creative Writing14911108
LMArena Multi-Turn14991113
EQ-Bench Creative Writing2133—
EQ-Bench 41385—

Frequently asked questions

Is Claude Opus 5 better than Yi-34B?

Claude Opus 5 is the stronger model overall, scoring 67.8 to 27.8 on the Noometry Index.

Is Claude Opus 5 or Yi-34B better for coding?

Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 32.3 in the Noometry coding category.

How many benchmarks do Claude Opus 5 and Yi-34B share?

19 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and Yi-34B has 23.

Related comparisons

Go deeper