Noometry

Model comparison

DeepSeek LLM 67B vs Qwen3 235B-A22B

Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 24.9 on the Noometry Index.

Last verified . 15 shared benchmarks.

DeepSeek LLM 67B DeepSeek

24.9

Rank #347 Confirmed

Qwen3 235B-A22B Alibaba (Qwen)

43.5

Rank #91 Confirmed

Summary

  • They share 15 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 1 category and Qwen3 235B-A22B in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3 235B-A22B leads 49.6 to 7.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 86.7% for Qwen3 235B-A22B.

Side by side

DeepSeek LLM 67BQwen3 235B-A22B
ProviderDeepSeekAlibaba (Qwen)
Noometry Index24.943.5
Released2023-11-292025-04
WeightsOpenOpen
Context window—131K
Max output—16K
Input $ / M tokens—$0.70
Output $ / M tokens—$2.80
Results tracked1549

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

Category by category

Coding Qwen3 235B-A22B leads

DeepSeek LLM 67B: 31.9 (#278), Qwen3 235B-A22B: 44.3 (#75)

BenchmarkDeepSeek LLM 67BQwen3 235B-A22B
LMArena Coding10961445
Aider Polyglot—59.6%
SciCode—42.4%
WeirdML—41%

Agentic & Tool Use Not comparable

DeepSeek LLM 67B: —, Qwen3 235B-A22B: 33.9 (#51)

BenchmarkDeepSeek LLM 67BQwen3 235B-A22B
Berkeley Function Calling Leaderboard—52.1%
Vending-Bench 2—-11.34

Reasoning Too close to call

DeepSeek LLM 67B: 16.5 (#304), Qwen3 235B-A22B: 15.7 (#311)

BenchmarkDeepSeek LLM 67BQwen3 235B-A22B
Chess Puzzles0%12%
LMArena Hard Prompts10701433
Epoch Capabilities Index110.5143.85
ARC-AGI-2—1.3%
SimpleBench—31%
Kagi LLM Benchmark—69.4%
ARC-AGI-1—11%
CritPt—0%
Mystery Game Puzzles—9%
DTBench—80.3%
LMCA—29.3%
ForecastBench—59.7

Math Qwen3 235B-A22B leads

DeepSeek LLM 67B: 8.7 (#324), Qwen3 235B-A22B: 50.4 (#57)

BenchmarkDeepSeek LLM 67BQwen3 235B-A22B
OTIS Mock AIME 2024-20250.8%86.7%
LMArena Math11081432
MATH Level 56.4%68.9%
Omni-MATH—71.8%
FrontierMath (Feb 2025 set)—8.5%
FrontierMath Tier 4 (v1)—0%

Knowledge Qwen3 235B-A22B leads

DeepSeek LLM 67B: 7.0 (#313), Qwen3 235B-A22B: 49.6 (#73)

BenchmarkDeepSeek LLM 67BQwen3 235B-A22B
GPQA Diamond24.6%80.1%
SimpleQA Verified—40.4%
MMLU-Pro—84.4%
Confabulations—15.6%
Vectara Hallucination Rate—9.3%
GPQA (HELM)—72.7%
LMArena Expert—1463

Multilingual Qwen3 235B-A22B leads

DeepSeek LLM 67B: 29.4 (#267), Qwen3 235B-A22B: 52.3 (#89)

BenchmarkDeepSeek LLM 67BQwen3 235B-A22B
LMArena Non-English10731409
LMArena Chinese11321481
LMArena French—1445
LMArena German—1433
LMArena Japanese—1399
LMArena Korean—1391
LMArena Russian—1411
LMArena Spanish—1430

Instruction Following Qwen3 235B-A22B leads

DeepSeek LLM 67B: 55.4 (#277), Qwen3 235B-A22B: 72.6 (#136)

BenchmarkDeepSeek LLM 67BQwen3 235B-A22B
LMArena Instruction Following10791408
IFEval—83.5%

Long Context Qwen3 235B-A22B leads

DeepSeek LLM 67B: 33.1 (#265), Qwen3 235B-A22B: 46.1 (#26)

BenchmarkDeepSeek LLM 67BQwen3 235B-A22B
LMArena Longer Query10921426
Fiction.LiveBench—75%

Writing & Preference Qwen3 235B-A22B leads

DeepSeek LLM 67B: 31.6 (#282), Qwen3 235B-A22B: 59.6 (#108)

BenchmarkDeepSeek LLM 67BQwen3 235B-A22B
LMArena Text11051419
LMArena Creative Writing10671384
LMArena Multi-Turn10821432
Short-Story Creative Writing—83%
EQ-Bench Creative Writing—1366
WildBench—86.6%

Frequently asked questions

Is DeepSeek LLM 67B better than Qwen3 235B-A22B?

Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 24.9 on the Noometry Index.

Is DeepSeek LLM 67B or Qwen3 235B-A22B better for coding?

Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 31.9 in the Noometry coding category.

How many benchmarks do DeepSeek LLM 67B and Qwen3 235B-A22B share?

15 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Qwen3 235B-A22B has 49.

Related comparisons

Go deeper