Noometry

Model comparison

Mixtral 8x22B vs Qwen2.5-Max

Qwen2.5-Max is the stronger model overall, scoring 40.7 to 27.1 on the Noometry Index.

Last verified . 18 shared benchmarks.

Mixtral 8x22B Mistral AI

27.1

Rank #333 Confirmed

Qwen2.5-Max Alibaba (Qwen)

40.7

Rank #146 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Mixtral 8x22B scores higher in 0 categories and Qwen2.5-Max in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen2.5-Max leads 35.3 to 15.1.
  • Mixtral 8x22B has downloadable open weights; the other is API-only.

Side by side

Mixtral 8x22BQwen2.5-Max
ProviderMistral AIAlibaba (Qwen)
Noometry Index27.140.7
Released2024-04-172025-01-25
WeightsOpenProprietary
Context window64K—
Max output64K—
Input $ / M tokens$2—
Output $ / M tokens$6—
Results tracked3427

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

Category by category

Coding Qwen2.5-Max leads

Mixtral 8x22B: 24.2 (#329), Qwen2.5-Max: 41.8 (#117)

BenchmarkMixtral 8x22BQwen2.5-Max
LMArena Coding11661359
WeirdML3.2%—
BigCodeBench Instruct40.6%—
LiveBench Coding—64.4%
BigCodeBench Complete50.2%—
HumanEval+72%—
MBPP+64.3%—

Agentic & Tool Use Not comparable

Mixtral 8x22B: 23.1 (#127), Qwen2.5-Max: —

BenchmarkMixtral 8x22BQwen2.5-Max
Cybench7.5%—

Reasoning Qwen2.5-Max leads

Mixtral 8x22B: 19.9 (#248), Qwen2.5-Max: 25.6 (#147)

BenchmarkMixtral 8x22BQwen2.5-Max
LMArena Hard Prompts11501360
Epoch Capabilities Index122.03132.53
LiveBench Reasoning—51.4%
DTBench55.1%—
LiveBench Data Analysis—67.9%
ForecastBench56.3—
LiveBench—62.3%

Math Qwen2.5-Max leads

Mixtral 8x22B: 22.9 (#275), Qwen2.5-Max: 36.9 (#162)

BenchmarkMixtral 8x22BQwen2.5-Max
LMArena Math11841369
Omni-MATH16.3%—
LiveBench Math—58.4%
MATH Level 524.2%—

Knowledge Qwen2.5-Max leads

Mixtral 8x22B: 15.1 (#293), Qwen2.5-Max: 35.3 (#186)

BenchmarkMixtral 8x22BQwen2.5-Max
LMArena Expert11131337
GPQA Diamond34.1%—
MMLU-Pro46%—
Confabulations—21.8%
GPQA (HELM)33.4%—
MMLU77.8%—

Multilingual Qwen2.5-Max leads

Mixtral 8x22B: 32.8 (#255), Qwen2.5-Max: 48.1 (#146)

BenchmarkMixtral 8x22BQwen2.5-Max
LMArena Non-English11281352
LMArena Chinese11161382
LMArena French11661396
LMArena German11411350
LMArena Japanese10371300
LMArena Korean10571304
LMArena Russian11581353
LMArena Spanish11511377

Instruction Following Qwen2.5-Max leads

Mixtral 8x22B: 57.7 (#266), Qwen2.5-Max: 71.3 (#152)

BenchmarkMixtral 8x22BQwen2.5-Max
LMArena Instruction Following11471335
LiveBench Instruction Following—75.3%
IFEval72.4%—

Long Context Qwen2.5-Max leads

Mixtral 8x22B: 34.7 (#247), Qwen2.5-Max: 41.4 (#142)

BenchmarkMixtral 8x22BQwen2.5-Max
LMArena Longer Query11441358

Writing & Preference Qwen2.5-Max leads

Mixtral 8x22B: 36.9 (#262), Qwen2.5-Max: 55.4 (#146)

BenchmarkMixtral 8x22BQwen2.5-Max
LMArena Text11621367
LMArena Creative Writing11411339
LMArena Multi-Turn11301364
Short-Story Creative Writing—72.9%
WildBench71.1%—
LiveBench Language—56.3%

Frequently asked questions

Is Mixtral 8x22B better than Qwen2.5-Max?

Qwen2.5-Max is the stronger model overall, scoring 40.7 to 27.1 on the Noometry Index.

Is Mixtral 8x22B or Qwen2.5-Max better for coding?

Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 24.2 in the Noometry coding category.

How many benchmarks do Mixtral 8x22B and Qwen2.5-Max share?

18 benchmarks have published results for both models. Mixtral 8x22B has 34 scored results on Noometry and Qwen2.5-Max has 27.

Related comparisons

Go deeper