Noometry

Model comparison

Mixtral 8x22B vs Qwen3.5 397B-A17B

Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 27.1 on the Noometry Index.

Last verified . 20 shared benchmarks.

Mixtral 8x22B Mistral AI

27.1

Rank #333 Confirmed

Qwen3.5 397B-A17B Alibaba (Qwen)

46.0

Rank #67 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Mixtral 8x22B scores higher in 0 categories and Qwen3.5 397B-A17B in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3.5 397B-A17B leads 53.3 to 15.1.
  • The biggest single-benchmark swing is GPQA Diamond: 34.1% for Mixtral 8x22B and 86.4% for Qwen3.5 397B-A17B.
  • Qwen3.5 397B-A17B is cheaper at $0.60 / $3.60 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
  • Qwen3.5 397B-A17B accepts more context: 262K tokens versus 64K.

Side by side

Mixtral 8x22BQwen3.5 397B-A17B
ProviderMistral AIAlibaba (Qwen)
Noometry Index27.146.0
Released2024-04-172026-02-01
WeightsOpenOpen
Context window64K262K
Max output64K66K
Input $ / M tokens$2$0.60
Output $ / M tokens$6$3.60
Results tracked3436

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

Category by category

Coding Qwen3.5 397B-A17B leads

Mixtral 8x22B: 24.2 (#329), Qwen3.5 397B-A17B: 42.0 (#114)

BenchmarkMixtral 8x22BQwen3.5 397B-A17B
LMArena Coding11661465
LMArena WebDev—1400
WeirdML3.2%—
BigCodeBench Instruct40.6%—
BigCodeBench Complete50.2%—
HumanEval+72%—
MBPP+64.3%—

Agentic & Tool Use Qwen3.5 397B-A17B leads

Mixtral 8x22B: 23.1 (#127), Qwen3.5 397B-A17B: 33.3 (#53)

BenchmarkMixtral 8x22BQwen3.5 397B-A17B
APEX-Agents—24.9%
τ²-bench Airline—81.5%
τ²-bench Banking—9.8%
τ²-bench Retail—84.4%
τ²-bench Telecom—97.8%
Cybench7.5%—

Reasoning Qwen3.5 397B-A17B leads

Mixtral 8x22B: 19.9 (#248), Qwen3.5 397B-A17B: 34.5 (#70)

BenchmarkMixtral 8x22BQwen3.5 397B-A17B
LMArena Hard Prompts11501448
DTBench55.1%87.5%
Epoch Capabilities Index122.03146.65
Kagi LLM Benchmark—73.7%
NYT Connections (extended)—58.9%
Chess Puzzles—13%
Thematic Generalization—65.1%
Mystery Game Puzzles—18%
LMCA—37.9%
ForecastBench56.3—

Math Qwen3.5 397B-A17B leads

Mixtral 8x22B: 22.9 (#275), Qwen3.5 397B-A17B: 46.1 (#73)

BenchmarkMixtral 8x22BQwen3.5 397B-A17B
LMArena Math11841454
FrontierMath (Tiers 1-3)—31.2%
OTIS Mock AIME 2024-2025—88.9%
Omni-MATH16.3%—
MATH Level 524.2%—

Knowledge Qwen3.5 397B-A17B leads

Mixtral 8x22B: 15.1 (#293), Qwen3.5 397B-A17B: 53.3 (#58)

BenchmarkMixtral 8x22BQwen3.5 397B-A17B
GPQA Diamond34.1%86.4%
LMArena Expert11131462
MMLU-Pro46%—
GPQA (HELM)33.4%—
MMLU77.8%—

Multimodal Not comparable

Mixtral 8x22B: —, Qwen3.5 397B-A17B: 40.7 (#44)

BenchmarkMixtral 8x22BQwen3.5 397B-A17B
LMArena Vision—1263

Multilingual Qwen3.5 397B-A17B leads

Mixtral 8x22B: 32.8 (#255), Qwen3.5 397B-A17B: 53.7 (#59)

BenchmarkMixtral 8x22BQwen3.5 397B-A17B
LMArena Non-English11281430
LMArena Chinese11161500
LMArena French11661461
LMArena German11411447
LMArena Japanese10371426
LMArena Korean10571384
LMArena Russian11581429
LMArena Spanish11511441

Instruction Following Qwen3.5 397B-A17B leads

Mixtral 8x22B: 57.7 (#266), Qwen3.5 397B-A17B: 75.0 (#77)

BenchmarkMixtral 8x22BQwen3.5 397B-A17B
LMArena Instruction Following11471424
IFEval72.4%—

Long Context Qwen3.5 397B-A17B leads

Mixtral 8x22B: 34.7 (#247), Qwen3.5 397B-A17B: 44.1 (#74)

BenchmarkMixtral 8x22BQwen3.5 397B-A17B
LMArena Longer Query11441442

Writing & Preference Qwen3.5 397B-A17B leads

Mixtral 8x22B: 36.9 (#262), Qwen3.5 397B-A17B: 62.3 (#79)

BenchmarkMixtral 8x22BQwen3.5 397B-A17B
LMArena Text11621438
LMArena Creative Writing11411401
LMArena Multi-Turn11301446
EQ-Bench Creative Writing—1478
WildBench71.1%—

Frequently asked questions

Is Mixtral 8x22B better than Qwen3.5 397B-A17B?

Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 27.1 on the Noometry Index.

Which is cheaper, Mixtral 8x22B or Qwen3.5 397B-A17B?

Qwen3.5 397B-A17B is cheaper. It lists at $0.60 per million input tokens and $3.60 per million output tokens; Mixtral 8x22B lists at $2 and $6.

Is Mixtral 8x22B or Qwen3.5 397B-A17B better for coding?

Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 24.2 in the Noometry coding category.

Which has the bigger context window?

Qwen3.5 397B-A17B does, with 262K tokens against 64K.

How many benchmarks do Mixtral 8x22B and Qwen3.5 397B-A17B share?

20 benchmarks have published results for both models. Mixtral 8x22B has 34 scored results on Noometry and Qwen3.5 397B-A17B has 36.

Related comparisons

Go deeper