Noometry

Model comparison

Qwen3.7 Plus vs Yi-34B

Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 27.8 on the Noometry Index.

Last verified . 19 shared benchmarks.

Qwen3.7 Plus Alibaba (Qwen)

45.3

Rank #72 Confirmed

Yi-34B 01.AI

27.8

Rank #329 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Qwen3.7 Plus 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 Qwen3.7 Plus leads 54.9 to 7.5.
  • The biggest single-benchmark swing is GPQA Diamond: 87.9% for Qwen3.7 Plus and 14.7% for Yi-34B.
  • Yi-34B has downloadable open weights; the other is API-only.

Side by side

Qwen3.7 PlusYi-34B
ProviderAlibaba (Qwen)01.AI
Noometry Index45.327.8
Released2026-06-022023-11-02
WeightsProprietaryOpen
Context window1M—
Max output131K—
Input $ / M tokens$0.40—
Output $ / M tokens$1.60—
Results tracked3223

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

Category by category

Coding Qwen3.7 Plus leads

Qwen3.7 Plus: 36.6 (#206), Yi-34B: 32.3 (#274)

BenchmarkQwen3.7 PlusYi-34B
LMArena Coding14731112
FrontierCode10.2%—
SciCode45.5%—

Agentic & Tool Use Not comparable

Qwen3.7 Plus: 21.4 (#138), Yi-34B: —

BenchmarkQwen3.7 PlusYi-34B
OSWorld 2.02.8%—

Reasoning Qwen3.7 Plus leads

Qwen3.7 Plus: 39.3 (#59), Yi-34B: 21.2 (#226)

BenchmarkQwen3.7 PlusYi-34B
LMArena Hard Prompts14601104
Epoch Capabilities Index147.37117.39
NYT Connections (extended)74.8%—
CritPt9.1%—
Chess Puzzles24%—
Mystery Game Puzzles17%—
DTBench84%—
LMCA37.6%—
BIG-Bench Hard—71.7%

Math Qwen3.7 Plus leads

Qwen3.7 Plus: 50.5 (#56), Yi-34B: 21.6 (#282)

BenchmarkQwen3.7 PlusYi-34B
LMArena Math14661114
FrontierMath (Tiers 1-3)34.4%—
OTIS Mock AIME 2024-202593.3%—
MATH Level 5—5.1%
GSM8K—76%

Knowledge Qwen3.7 Plus leads

Qwen3.7 Plus: 54.9 (#51), Yi-34B: 7.5 (#309)

BenchmarkQwen3.7 PlusYi-34B
GPQA Diamond87.9%14.7%
LMArena Expert14671061
MMLU—76.3%

Multimodal Not comparable

Qwen3.7 Plus: 41.8 (#33), Yi-34B: —

BenchmarkQwen3.7 PlusYi-34B
LMArena Vision1279—
LMArena Document1444—

Multilingual Qwen3.7 Plus leads

Qwen3.7 Plus: 54.8 (#38), Yi-34B: 29.7 (#264)

BenchmarkQwen3.7 PlusYi-34B
LMArena Non-English14451079
LMArena Chinese15101176
LMArena French14731081
LMArena German14711042
LMArena Japanese1413993
LMArena Korean1415959
LMArena Russian14571050
LMArena Spanish14571070

Instruction Following Qwen3.7 Plus leads

Qwen3.7 Plus: 75.8 (#52), Yi-34B: 56.2 (#274)

BenchmarkQwen3.7 PlusYi-34B
LMArena Instruction Following14401091

Long Context Qwen3.7 Plus leads

Qwen3.7 Plus: 44.5 (#65), Yi-34B: 33.2 (#264)

BenchmarkQwen3.7 PlusYi-34B
LMArena Longer Query14551094

Writing & Preference Qwen3.7 Plus leads

Qwen3.7 Plus: 64.3 (#56), Yi-34B: 34.1 (#273)

BenchmarkQwen3.7 PlusYi-34B
LMArena Text14551129
LMArena Creative Writing14391108
LMArena Multi-Turn14601113

Frequently asked questions

Is Qwen3.7 Plus better than Yi-34B?

Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 27.8 on the Noometry Index.

Is Qwen3.7 Plus or Yi-34B better for coding?

Qwen3.7 Plus scores higher on coding benchmarks: 36.6 versus 32.3 in the Noometry coding category.

How many benchmarks do Qwen3.7 Plus and Yi-34B share?

19 benchmarks have published results for both models. Qwen3.7 Plus has 32 scored results on Noometry and Yi-34B has 23.

Related comparisons

Go deeper