Noometry

Model comparison

Qwen3.5-Flash vs Yi-34B

Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 27.8 on the Noometry Index.

Last verified . 19 shared benchmarks.

Qwen3.5-Flash Alibaba (Qwen)

42.5

Rank #112 Confirmed

Yi-34B 01.AI

27.8

Rank #329 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Qwen3.5-Flash 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 Qwen3.5-Flash leads 43.2 to 7.5.
  • The biggest single-benchmark swing is GPQA Diamond: 82.3% for Qwen3.5-Flash and 14.7% for Yi-34B.
  • Yi-34B has downloadable open weights; the other is API-only.

Side by side

Qwen3.5-FlashYi-34B
ProviderAlibaba (Qwen)01.AI
Noometry Index42.527.8
Released2026-02-232023-11-02
WeightsProprietaryOpen
Context window1M—
Max output66K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.40—
Results tracked3223

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

Category by category

Coding Qwen3.5-Flash leads

Qwen3.5-Flash: 34.2 (#242), Yi-34B: 32.3 (#274)

BenchmarkQwen3.5-FlashYi-34B
LMArena Coding14121112
LMArena WebDev1244—
ALE-Bench221.8—

Agentic & Tool Use Not comparable

Qwen3.5-Flash: —, Yi-34B: —

BenchmarkQwen3.5-FlashYi-34B
Vending-Bench 2462.69—

Reasoning Qwen3.5-Flash leads

Qwen3.5-Flash: 33.7 (#72), Yi-34B: 21.2 (#226)

BenchmarkQwen3.5-FlashYi-34B
LMArena Hard Prompts14031104
Epoch Capabilities Index143.98117.39
Chess Puzzles21%—
Mystery Game Puzzles20%—
DTBench82.9%—
LMCA29.1%—
BIG-Bench Hard—71.7%

Math Qwen3.5-Flash leads

Qwen3.5-Flash: 37.4 (#158), Yi-34B: 21.6 (#282)

BenchmarkQwen3.5-FlashYi-34B
LMArena Math14071114
FrontierMath (Tiers 1-3)18.2%—
OTIS Mock AIME 2024-202584.4%—
MATH Level 5—5.1%
FrontierMath (Feb 2025 set)6.2%—
FrontierMath Tier 4 (v1)0%—
GSM8K—76%

Knowledge Qwen3.5-Flash leads

Qwen3.5-Flash: 43.2 (#93), Yi-34B: 7.5 (#309)

BenchmarkQwen3.5-FlashYi-34B
GPQA Diamond82.3%14.7%
LMArena Expert14071061
SimpleQA Verified20.3%—
Vectara Hallucination Rate10.5%—
MMLU—76.3%

Multilingual Qwen3.5-Flash leads

Qwen3.5-Flash: 50.5 (#121), Yi-34B: 29.7 (#264)

BenchmarkQwen3.5-FlashYi-34B
LMArena Non-English13851079
LMArena Chinese14461176
LMArena French14121081
LMArena German13901042
LMArena Japanese1368993
LMArena Korean1344959
LMArena Russian13791050
LMArena Spanish14001070

Instruction Following Qwen3.5-Flash leads

Qwen3.5-Flash: 72.6 (#139), Yi-34B: 56.2 (#274)

BenchmarkQwen3.5-FlashYi-34B
LMArena Instruction Following13741091

Long Context Qwen3.5-Flash leads

Qwen3.5-Flash: 42.4 (#124), Yi-34B: 33.2 (#264)

BenchmarkQwen3.5-FlashYi-34B
LMArena Longer Query13921094

Writing & Preference Qwen3.5-Flash leads

Qwen3.5-Flash: 57.9 (#122), Yi-34B: 34.1 (#273)

BenchmarkQwen3.5-FlashYi-34B
LMArena Text13971129
LMArena Creative Writing13431108
LMArena Multi-Turn13931113

Frequently asked questions

Is Qwen3.5-Flash better than Yi-34B?

Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 27.8 on the Noometry Index.

Is Qwen3.5-Flash or Yi-34B better for coding?

Qwen3.5-Flash scores higher on coding benchmarks: 34.2 versus 32.3 in the Noometry coding category.

How many benchmarks do Qwen3.5-Flash and Yi-34B share?

19 benchmarks have published results for both models. Qwen3.5-Flash has 32 scored results on Noometry and Yi-34B has 23.

Related comparisons

Go deeper