Model comparison

DeepSeek-V2.5 (Sep 2024) vs Hunyuan Large 2025 02 10

DeepSeek-V2.5 (Sep 2024) and Hunyuan Large 2025 02 10 score almost the same on the Noometry Index (37.0 vs 38.0), so choose on price, context window or the category you care about most.

Last verified . 12 shared benchmarks.

DeepSeek-V2.5 (Sep 2024) DeepSeek

37.0

Rank #197 Confirmed

Hunyuan Large 2025 02 10 Tencent

38.0

Rank #183 Confirmed

Summary

  • They share 12 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 5 categories and Hunyuan Large 2025 02 10 in 3 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Hunyuan Large 2025 02 10 leads 37.6 to 31.3.
  • DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.

Side by side

DeepSeek-V2.5 (Sep 2024) and Hunyuan Large 2025 02 10 specifications
DeepSeek-V2.5 (Sep 2024)Hunyuan Large 2025 02 10
ProviderDeepSeekTencent
Noometry Index37.038.0
Released2024-09-06—
WeightsOpenProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked2212

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

Category by category

Coding Hunyuan Large 2025 02 10 leads

DeepSeek-V2.5 (Sep 2024): 31.3 (#274), Hunyuan Large 2025 02 10: 37.6 (#177)

Coding benchmarks
BenchmarkDeepSeek-V2.5 (Sep 2024)Hunyuan Large 2025 02 10
LMArena Coding13101307
Aider Polyglot17.8%—
BigCodeBench Instruct48.6%—
BigCodeBench Complete53.2%—
HumanEval+83.5%—
MBPP+74.1%—

Reasoning Too close to call

DeepSeek-V2.5 (Sep 2024): 24.5 (#145), Hunyuan Large 2025 02 10: 24.5 (#147)

Reasoning benchmarks
BenchmarkDeepSeek-V2.5 (Sep 2024)Hunyuan Large 2025 02 10
LMArena Hard Prompts12891286

Math Too close to call

DeepSeek-V2.5 (Sep 2024): 33.3 (#177), Hunyuan Large 2025 02 10: 33.1 (#178)

Math benchmarks
BenchmarkDeepSeek-V2.5 (Sep 2024)Hunyuan Large 2025 02 10
LMArena Math12891281

Knowledge Too close to call

DeepSeek-V2.5 (Sep 2024): 34.2 (#190), Hunyuan Large 2025 02 10: 34.5 (#188)

Knowledge benchmarks
BenchmarkDeepSeek-V2.5 (Sep 2024)Hunyuan Large 2025 02 10
LMArena Expert12661276

Multilingual Too close to call

DeepSeek-V2.5 (Sep 2024): 42.7 (#188), Hunyuan Large 2025 02 10: 42.1 (#195)

Multilingual benchmarks
BenchmarkDeepSeek-V2.5 (Sep 2024)Hunyuan Large 2025 02 10
LMArena Non-English12731265
LMArena Chinese13171346
LMArena Russian12891266
LMArena French1288—
LMArena German1258—
LMArena Japanese1228—
LMArena Korean1209—
LMArena Spanish1248—

Instruction Following Too close to call

DeepSeek-V2.5 (Sep 2024): 67.7 (#189), Hunyuan Large 2025 02 10: 67.6 (#192)

Instruction Following benchmarks
BenchmarkDeepSeek-V2.5 (Sep 2024)Hunyuan Large 2025 02 10
LMArena Instruction Following12801277

Long Context Hunyuan Large 2025 02 10 leads

DeepSeek-V2.5 (Sep 2024): 39.5 (#169), Hunyuan Large 2025 02 10: 40.8 (#144)

Long Context benchmarks
BenchmarkDeepSeek-V2.5 (Sep 2024)Hunyuan Large 2025 02 10
LMArena Longer Query13011342

Writing & Preference DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 50.0 (#182), Hunyuan Large 2025 02 10: 48.9 (#191)

Writing & Preference benchmarks
BenchmarkDeepSeek-V2.5 (Sep 2024)Hunyuan Large 2025 02 10
LMArena Text12941288
LMArena Creative Writing12851264
LMArena Multi-Turn12971284

Frequently asked questions

Is DeepSeek-V2.5 (Sep 2024) better than Hunyuan Large 2025 02 10?

DeepSeek-V2.5 (Sep 2024) and Hunyuan Large 2025 02 10 score almost the same on the Noometry Index (37.0 vs 38.0), so choose on price, context window or the category you care about most.

Is DeepSeek-V2.5 (Sep 2024) or Hunyuan Large 2025 02 10 better for coding?

Hunyuan Large 2025 02 10 scores higher on coding benchmarks: 37.6 versus 31.3 in the Noometry coding category.

How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Hunyuan Large 2025 02 10 share?

12 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Hunyuan Large 2025 02 10 has 12.

Related comparisons

Go deeper