Noometry

Model comparison

DeepSeek-R1-Distill-Llama-70B vs Qwen Max

DeepSeek-R1-Distill-Llama-70B is the stronger model overall, scoring 37.8 to 34.7 on the Noometry Index.

Last verified . 3 shared benchmarks.

DeepSeek-R1-Distill-Llama-70B DeepSeek

37.8

Rank #195 Confirmed

Qwen Max Alibaba (Qwen)

34.7

Rank #230 Confirmed

Summary

  • They share 3 benchmarks with published results for both. DeepSeek-R1-Distill-Llama-70B scores higher in 5 categories and Qwen Max in 1 category; 4 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek-R1-Distill-Llama-70B leads 36.0 to 22.3.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 51.4% for DeepSeek-R1-Distill-Llama-70B and 16.1% for Qwen Max.
  • DeepSeek-R1-Distill-Llama-70B has downloadable open weights; the other is API-only.

Side by side

DeepSeek-R1-Distill-Llama-70BQwen Max
ProviderDeepSeekAlibaba (Qwen)
Noometry Index37.834.7
Released2025-01-202024-04-03
WeightsOpenProprietary
Context window—33K
Max output—8K
Input $ / M tokens—$1.60
Output $ / M tokens—$6.40
Results tracked1323

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

Category by category

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

DeepSeek-R1-Distill-Llama-70B: 36.8 (#202), Qwen Max: 30.7 (#292)

BenchmarkDeepSeek-R1-Distill-Llama-70BQwen Max
Aider Polyglot—21.8%
BigCodeBench Instruct35.3%—
LiveBench Coding51.6%—
LMArena Coding—1288
BigCodeBench Complete49.9%—

Reasoning Too close to call

DeepSeek-R1-Distill-Llama-70B: 24.9 (#156), Qwen Max: 25.1 (#151)

BenchmarkDeepSeek-R1-Distill-Llama-70BQwen Max
Kagi LLM Benchmark52.3%—
LiveBench Reasoning67.6%—
LMArena Hard Prompts—1269
LiveBench Data Analysis55.9%—
LiveBench54.5%—

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

DeepSeek-R1-Distill-Llama-70B: 36.0 (#176), Qwen Max: 22.3 (#276)

BenchmarkDeepSeek-R1-Distill-Llama-70BQwen Max
OTIS Mock AIME 2024-202551.4%16.1%
MATH Level 589.9%67.2%
LiveBench Math58.1%—
LMArena Math—1275
FrontierMath (Feb 2025 set)—1%

Knowledge Too close to call

DeepSeek-R1-Distill-Llama-70B: 30.7 (#225), Qwen Max: 30.3 (#228)

BenchmarkDeepSeek-R1-Distill-Llama-70BQwen Max
GPQA Diamond55.7%56.1%
LMArena Expert—1248

Multilingual Not comparable

DeepSeek-R1-Distill-Llama-70B: —, Qwen Max: 41.8 (#202)

BenchmarkDeepSeek-R1-Distill-Llama-70BQwen Max
LMArena Non-English—1263
LMArena Chinese—1254
LMArena French—1330
LMArena German—1254
LMArena Japanese—1205
LMArena Korean—1142
LMArena Russian—1274
LMArena Spanish—1290

Instruction Following DeepSeek-R1-Distill-Llama-70B leads

DeepSeek-R1-Distill-Llama-70B: 68.2 (#190), Qwen Max: 66.5 (#208)

BenchmarkDeepSeek-R1-Distill-Llama-70BQwen Max
LiveBench Instruction Following69.9%—
LMArena Instruction Following—1262

Long Context Not comparable

DeepSeek-R1-Distill-Llama-70B: —, Qwen Max: 39.4 (#180)

BenchmarkDeepSeek-R1-Distill-Llama-70BQwen Max
Fiction.LiveBench—66.7%
LMArena Longer Query—1288

Writing & Preference DeepSeek-R1-Distill-Llama-70B leads

DeepSeek-R1-Distill-Llama-70B: 49.0 (#194), Qwen Max: 47.8 (#205)

BenchmarkDeepSeek-R1-Distill-Llama-70BQwen Max
LMArena Text—1282
LMArena Creative Writing—1248
LMArena Multi-Turn—1277
LiveBench Language23.8%—

Frequently asked questions

Is DeepSeek-R1-Distill-Llama-70B better than Qwen Max?

DeepSeek-R1-Distill-Llama-70B is the stronger model overall, scoring 37.8 to 34.7 on the Noometry Index.

Is DeepSeek-R1-Distill-Llama-70B or Qwen Max better for coding?

DeepSeek-R1-Distill-Llama-70B scores higher on coding benchmarks: 36.8 versus 30.7 in the Noometry coding category.

How many benchmarks do DeepSeek-R1-Distill-Llama-70B and Qwen Max share?

3 benchmarks have published results for both models. DeepSeek-R1-Distill-Llama-70B has 13 scored results on Noometry and Qwen Max has 23.

Related comparisons

Go deeper