Noometry

Model comparison

DeepSeek V4.1 Flash vs ERNIE 5.0 0110

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 41.8 on the Noometry Index.

Last verified . 19 shared benchmarks.

DeepSeek V4.1 Flash DeepSeek

52.8

Rank #38 Confirmed

ERNIE 5.0 0110 Baidu

41.8

Rank #129 Confirmed

Summary

  • They share 19 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and ERNIE 5.0 0110 in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 50.2 to 17.0.
  • The biggest single-benchmark swing is NYT Connections (extended): 89.6% for DeepSeek V4.1 Flash and 10.3% for ERNIE 5.0 0110.
  • DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.

Side by side

DeepSeek V4.1 FlashERNIE 5.0 0110
ProviderDeepSeekBaidu
Noometry Index52.841.8
Released2026-09-09—
WeightsOpenProprietary
Context window1M—
Max output393K—
Input $ / M tokens$0.15—
Output $ / M tokens$0.60—
Results tracked3720

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), ERNIE 5.0 0110: 43.0 (#94)

BenchmarkDeepSeek V4.1 FlashERNIE 5.0 0110
LMArena Coding15061455
LMArena WebDev1619—
SciCode51.9%—
ALE-Bench1,092—

Agentic & Tool Use Not comparable

DeepSeek V4.1 Flash: 31.2 (#69), ERNIE 5.0 0110: —

BenchmarkDeepSeek V4.1 FlashERNIE 5.0 0110
APEX-Agents39.5%—
GDP.pdf19.8%—

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 50.2 (#36), ERNIE 5.0 0110: 17.0 (#297)

BenchmarkDeepSeek V4.1 FlashERNIE 5.0 0110
NYT Connections (extended)89.6%10.3%
LMArena Hard Prompts14831445
CritPt14.3%—
Thematic Generalization—41.7%
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), ERNIE 5.0 0110: 39.3 (#110)

BenchmarkDeepSeek V4.1 FlashERNIE 5.0 0110
LMArena Math14771437
FrontierMath (Tiers 1-3)67.4%—
FrontierMath Tier 426.8%—
OTIS Mock AIME 2024-202598.3%—
ProofBench54%—

Knowledge DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 57.9 (#38), ERNIE 5.0 0110: 39.8 (#128)

BenchmarkDeepSeek V4.1 FlashERNIE 5.0 0110
LMArena Expert15061428
GPQA Diamond89.8%—

Multimodal Too close to call

DeepSeek V4.1 Flash: 39.1 (#61), ERNIE 5.0 0110: 39.9 (#53)

BenchmarkDeepSeek V4.1 FlashERNIE 5.0 0110
LMArena Vision12771249
Furniture Assembly34.2%—

Multilingual Too close to call

DeepSeek V4.1 Flash: 55.0 (#35), ERNIE 5.0 0110: 54.1 (#49)

BenchmarkDeepSeek V4.1 FlashERNIE 5.0 0110
LMArena Non-English14481436
LMArena Chinese14971512
LMArena French14521467
LMArena German14841460
LMArena Japanese14121382
LMArena Korean14521406
LMArena Russian14711446
LMArena Spanish14591473

Instruction Following DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 77.3 (#26), ERNIE 5.0 0110: 74.5 (#92)

BenchmarkDeepSeek V4.1 FlashERNIE 5.0 0110
LMArena Instruction Following14741413

Long Context DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 45.2 (#47), ERNIE 5.0 0110: 43.4 (#95)

BenchmarkDeepSeek V4.1 FlashERNIE 5.0 0110
LMArena Longer Query14751422

Writing & Preference DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 65.4 (#48), ERNIE 5.0 0110: 63.1 (#66)

BenchmarkDeepSeek V4.1 FlashERNIE 5.0 0110
LMArena Text14621445
LMArena Creative Writing14351426
LMArena Multi-Turn14571434
EQ-Bench Creative Writing1540—

Frequently asked questions

Is DeepSeek V4.1 Flash better than ERNIE 5.0 0110?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 41.8 on the Noometry Index.

Is DeepSeek V4.1 Flash or ERNIE 5.0 0110 better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 43.0 in the Noometry coding category.

How many benchmarks do DeepSeek V4.1 Flash and ERNIE 5.0 0110 share?

19 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and ERNIE 5.0 0110 has 20.

Related comparisons

Go deeper