Noometry

Model comparison

DeepSeek V4.1 Flash vs Yi-1.5-34B

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 30.6 on the Noometry Index.

Last verified . 18 shared benchmarks.

DeepSeek V4.1 Flash DeepSeek

52.8

Rank #38 Confirmed

Yi-1.5-34B 01.AI

30.6

Rank #289 Confirmed

Summary

  • They share 18 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and Yi-1.5-34B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where DeepSeek V4.1 Flash leads 57.9 to 14.8.
  • The biggest single-benchmark swing is GPQA Diamond: 89.8% for DeepSeek V4.1 Flash and 32% for Yi-1.5-34B.

Side by side

DeepSeek V4.1 FlashYi-1.5-34B
ProviderDeepSeek01.AI
Noometry Index52.830.6
Released2026-09-092024-05-13
WeightsOpenOpen
Context window1M—
Max output393K—
Input $ / M tokens$0.15—
Output $ / M tokens$0.60—
Results tracked3721

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

Category by category

Coding DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 52.9 (#32), Yi-1.5-34B: 32.4 (#272)

BenchmarkDeepSeek V4.1 FlashYi-1.5-34B
LMArena Coding15061169
LMArena WebDev1619—
SciCode51.9%—
BigCodeBench Instruct—33.9%
BigCodeBench Complete—43.8%
ALE-Bench1,092—

Agentic & Tool Use Not comparable

DeepSeek V4.1 Flash: 31.2 (#69), Yi-1.5-34B: —

BenchmarkDeepSeek V4.1 FlashYi-1.5-34B
APEX-Agents39.5%—
GDP.pdf19.8%—

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 50.2 (#36), Yi-1.5-34B: 22.5 (#191)

BenchmarkDeepSeek V4.1 FlashYi-1.5-34B
LMArena Hard Prompts14831160
NYT Connections (extended)89.6%—
CritPt14.3%—
Mystery Game Puzzles43%—
DTBench89.9%—
LMCA47%—
Surface Evolver Bench46.3%—
Epoch Capabilities Index154.9—

Math DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 66.7 (#25), Yi-1.5-34B: 27.5 (#249)

BenchmarkDeepSeek V4.1 FlashYi-1.5-34B
LMArena Math14771182
FrontierMath (Tiers 1-3)67.4%—
FrontierMath Tier 426.8%—
OTIS Mock AIME 2024-202598.3%—
ProofBench54%—
MATH Level 5—25.5%

Knowledge DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 57.9 (#38), Yi-1.5-34B: 14.8 (#295)

BenchmarkDeepSeek V4.1 FlashYi-1.5-34B
GPQA Diamond89.8%32%
LMArena Expert15061144

Multimodal Not comparable

DeepSeek V4.1 Flash: 39.1 (#61), Yi-1.5-34B: —

BenchmarkDeepSeek V4.1 FlashYi-1.5-34B
LMArena Vision1277—
Furniture Assembly34.2%—

Multilingual DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 55.0 (#35), Yi-1.5-34B: 32.3 (#256)

BenchmarkDeepSeek V4.1 FlashYi-1.5-34B
LMArena Non-English14481121
LMArena Chinese14971213
LMArena French14521156
LMArena German14841111
LMArena Japanese14121021
LMArena Korean14521005
LMArena Russian14711091
LMArena Spanish14591121

Instruction Following DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 77.3 (#26), Yi-1.5-34B: 59.2 (#257)

BenchmarkDeepSeek V4.1 FlashYi-1.5-34B
LMArena Instruction Following14741139

Long Context DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 45.2 (#47), Yi-1.5-34B: 34.6 (#248)

BenchmarkDeepSeek V4.1 FlashYi-1.5-34B
LMArena Longer Query14751143

Writing & Preference DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 65.4 (#48), Yi-1.5-34B: 37.4 (#257)

BenchmarkDeepSeek V4.1 FlashYi-1.5-34B
LMArena Text14621173
LMArena Creative Writing14351135
LMArena Multi-Turn14571153
EQ-Bench Creative Writing1540—

Frequently asked questions

Is DeepSeek V4.1 Flash better than Yi-1.5-34B?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 30.6 on the Noometry Index.

Is DeepSeek V4.1 Flash or Yi-1.5-34B better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 32.4 in the Noometry coding category.

How many benchmarks do DeepSeek V4.1 Flash and Yi-1.5-34B share?

18 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Yi-1.5-34B has 21.

Related comparisons

Go deeper