Noometry

Model comparison

DeepSeek-R1-Distill-Llama-70B vs MiMo-V2-Pro

MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 37.8 on the Noometry Index.

Last verified . 0 shared benchmarks.

DeepSeek-R1-Distill-Llama-70B DeepSeek

37.8

Rank #195 Confirmed

MiMo-V2-Pro Xiaomi

43.0

Rank #103 Confirmed

Summary

  • The widest gap is in writing & preference, where MiMo-V2-Pro leads 62.8 to 49.0.
  • DeepSeek-R1-Distill-Llama-70B has downloadable open weights; the other is API-only.

Side by side

DeepSeek-R1-Distill-Llama-70BMiMo-V2-Pro
ProviderDeepSeekXiaomi
Noometry Index37.843.0
Released2025-01-202026-03-18
WeightsOpenProprietary
Context window—1.05M
Max output—131K
Input $ / M tokens—$0.43
Output $ / M tokens—$0.87
Results tracked1323

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

Category by category

Coding MiMo-V2-Pro leads

DeepSeek-R1-Distill-Llama-70B: 36.8 (#202), MiMo-V2-Pro: 43.8 (#83)

BenchmarkDeepSeek-R1-Distill-Llama-70BMiMo-V2-Pro
LMArena WebDev—1433
BigCodeBench Instruct35.3%—
LiveBench Coding51.6%—
LMArena Coding—1476
BigCodeBench Complete49.9%—
ALE-Bench—785.17

Reasoning DeepSeek-R1-Distill-Llama-70B leads

DeepSeek-R1-Distill-Llama-70B: 24.9 (#156), MiMo-V2-Pro: 22.1 (#206)

BenchmarkDeepSeek-R1-Distill-Llama-70BMiMo-V2-Pro
Kagi LLM Benchmark52.3%—
NYT Connections (extended)—25.8%
Thematic Generalization—45.9%
LiveBench Reasoning67.6%—
LMArena Hard Prompts—1457
LiveBench Data Analysis55.9%—
LiveBench54.5%—

Math MiMo-V2-Pro leads

DeepSeek-R1-Distill-Llama-70B: 36.0 (#176), MiMo-V2-Pro: 39.5 (#102)

BenchmarkDeepSeek-R1-Distill-Llama-70BMiMo-V2-Pro
OTIS Mock AIME 2024-202551.4%—
LiveBench Math58.1%—
LMArena Math—1447
MATH Level 589.9%—

Knowledge MiMo-V2-Pro leads

DeepSeek-R1-Distill-Llama-70B: 30.7 (#225), MiMo-V2-Pro: 41.4 (#111)

BenchmarkDeepSeek-R1-Distill-Llama-70BMiMo-V2-Pro
GPQA Diamond55.7%—
LMArena Expert—1478

Multilingual Not comparable

DeepSeek-R1-Distill-Llama-70B: —, MiMo-V2-Pro: 52.7 (#81)

BenchmarkDeepSeek-R1-Distill-Llama-70BMiMo-V2-Pro
LMArena Non-English—1416
LMArena Chinese—1456
LMArena French—1469
LMArena German—1417
LMArena Japanese—1366
LMArena Korean—1400
LMArena Russian—1427
LMArena Spanish—1457

Instruction Following MiMo-V2-Pro leads

DeepSeek-R1-Distill-Llama-70B: 68.2 (#190), MiMo-V2-Pro: 76.0 (#49)

BenchmarkDeepSeek-R1-Distill-Llama-70BMiMo-V2-Pro
LiveBench Instruction Following69.9%—
LMArena Instruction Following—1445

Long Context Not comparable

DeepSeek-R1-Distill-Llama-70B: —, MiMo-V2-Pro: 41.5 (#138)

BenchmarkDeepSeek-R1-Distill-Llama-70BMiMo-V2-Pro
CL-bench—15.7%
CL-bench Life—6.9%
LMArena Longer Query—1455

Writing & Preference MiMo-V2-Pro leads

DeepSeek-R1-Distill-Llama-70B: 49.0 (#194), MiMo-V2-Pro: 62.8 (#70)

BenchmarkDeepSeek-R1-Distill-Llama-70BMiMo-V2-Pro
LMArena Text—1436
LMArena Creative Writing—1415
LMArena Multi-Turn—1456
LiveBench Language23.8%—

Frequently asked questions

Is DeepSeek-R1-Distill-Llama-70B better than MiMo-V2-Pro?

MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 37.8 on the Noometry Index.

Is DeepSeek-R1-Distill-Llama-70B or MiMo-V2-Pro better for coding?

MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 36.8 in the Noometry coding category.

How many benchmarks do DeepSeek-R1-Distill-Llama-70B and MiMo-V2-Pro share?

0 benchmarks have published results for both models. DeepSeek-R1-Distill-Llama-70B has 13 scored results on Noometry and MiMo-V2-Pro has 23.

Related comparisons

Go deeper