Noometry

Model comparison

Mixtral 8x22B vs Qwen2.5-VL 72B Instruct

Qwen2.5-VL 72B Instruct is the stronger model overall, scoring 29.4 to 26.7 on the Noometry Index.

Last verified . 0 shared benchmarks.

Mixtral 8x22B Mistral AI

26.7

Rank #330 Confirmed

Qwen2.5-VL 72B Instruct Alibaba (Qwen)

29.4

Rank #298 Confirmed

Summary

  • The widest gap is in agentic & tool use, where Mixtral 8x22B leads 22.8 to 18.4.
  • Mixtral 8x22B is cheaper at $2 / $6 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.
  • Qwen2.5-VL 72B Instruct accepts more context: 131K tokens versus 64K.

Side by side

Mixtral 8x22BQwen2.5-VL 72B Instruct
ProviderMistral AIAlibaba (Qwen)
Noometry Index26.729.4
Released2024-04-172024-09
WeightsOpenOpen
Context window64K131K
Max output64K8K
Input $ / M tokens$2$2.80
Output $ / M tokens$6$8.40
Results tracked346

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

Category by category

Coding Not comparable

Mixtral 8x22B: 23.8 (#324), Qwen2.5-VL 72B Instruct: —

BenchmarkMixtral 8x22BQwen2.5-VL 72B Instruct
WeirdML3.2%—
BigCodeBench Instruct40.6%—
LMArena Coding1166—
BigCodeBench Complete50.2%—
HumanEval+72%—
MBPP+64.3%—

Agentic & Tool Use Mixtral 8x22B leads

Mixtral 8x22B: 22.8 (#119), Qwen2.5-VL 72B Instruct: 18.4 (#136)

BenchmarkMixtral 8x22BQwen2.5-VL 72B Instruct
Cybench7.5%—
OSWorld—5%

Reasoning Too close to call

Mixtral 8x22B: 19.1 (#246), Qwen2.5-VL 72B Instruct: 20.0 (#228)

BenchmarkMixtral 8x22BQwen2.5-VL 72B Instruct
Kagi LLM Benchmark—36%
LMArena Hard Prompts1150—
DTBench55.1%—
Epoch Capabilities Index122—
ForecastBench56.3—

Math Not comparable

Mixtral 8x22B: 21.2 (#271), Qwen2.5-VL 72B Instruct: —

BenchmarkMixtral 8x22BQwen2.5-VL 72B Instruct
Omni-MATH16.3%—
LMArena Math1184—
MATH Level 524.2%—

Knowledge Not comparable

Mixtral 8x22B: 15.1 (#288), Qwen2.5-VL 72B Instruct: —

BenchmarkMixtral 8x22BQwen2.5-VL 72B Instruct
GPQA Diamond34.1%—
MMLU-Pro46%—
GPQA (HELM)33.4%—
LMArena Expert1113—
MMLU77.8%—

Multimodal Not comparable

Mixtral 8x22B: —, Qwen2.5-VL 72B Instruct: 32.9 (#92)

BenchmarkMixtral 8x22BQwen2.5-VL 72B Instruct
LMArena Vision—1107
Video-MME—73.5%
GeoBench—62%
SpatialViz-Bench—33.3%

Multilingual Not comparable

Mixtral 8x22B: 32.9 (#250), Qwen2.5-VL 72B Instruct: —

BenchmarkMixtral 8x22BQwen2.5-VL 72B Instruct
LMArena Non-English1128—
LMArena Chinese1116—
LMArena French1165—
LMArena German1141—
LMArena Japanese1037—
LMArena Korean1056—
LMArena Russian1158—
LMArena Spanish1150—

Instruction Following Not comparable

Mixtral 8x22B: 57.9 (#261), Qwen2.5-VL 72B Instruct: —

BenchmarkMixtral 8x22BQwen2.5-VL 72B Instruct
IFEval72.4%—
LMArena Instruction Following1147—

Long Context Not comparable

Mixtral 8x22B: 34.6 (#242), Qwen2.5-VL 72B Instruct: —

BenchmarkMixtral 8x22BQwen2.5-VL 72B Instruct
LMArena Longer Query1144—

Writing & Preference Not comparable

Mixtral 8x22B: 37.1 (#257), Qwen2.5-VL 72B Instruct: —

BenchmarkMixtral 8x22BQwen2.5-VL 72B Instruct
LMArena Text1162—
LMArena Creative Writing1141—
WildBench71.1%—
LMArena Multi-Turn1130—

Frequently asked questions

Is Mixtral 8x22B better than Qwen2.5-VL 72B Instruct?

Qwen2.5-VL 72B Instruct is the stronger model overall, scoring 29.4 to 26.7 on the Noometry Index.

Which is cheaper, Mixtral 8x22B or Qwen2.5-VL 72B Instruct?

Mixtral 8x22B is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Qwen2.5-VL 72B Instruct lists at $2.80 and $8.40.

Which has the bigger context window?

Qwen2.5-VL 72B Instruct does, with 131K tokens against 64K.

How many benchmarks do Mixtral 8x22B and Qwen2.5-VL 72B Instruct share?

0 benchmarks have published results for both models. Mixtral 8x22B has 34 scored results on Noometry and Qwen2.5-VL 72B Instruct has 6.

Related comparisons

Go deeper