Noometry

Model comparison

Mistral vs Qwen3.5 397B-A17B

Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 29.9 on the Noometry Index.

Last verified . 17 shared benchmarks.

Mistral Mistral AI

29.9

Rank #303 Confirmed

Qwen3.5 397B-A17B Alibaba (Qwen)

46.0

Rank #67 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Mistral scores higher in 0 categories and Qwen3.5 397B-A17B in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3.5 397B-A17B leads 53.3 to 16.6.
  • Qwen3.5 397B-A17B has downloadable open weights; the other is API-only.

Side by side

MistralQwen3.5 397B-A17B
ProviderMistral AIAlibaba (Qwen)
Noometry Index29.946.0
Released—2026-02-01
WeightsProprietaryOpen
Context window—262K
Max output—66K
Input $ / M tokens—$0.60
Output $ / M tokens—$3.60
Results tracked2236

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

Category by category

Coding Qwen3.5 397B-A17B leads

Mistral: 33.8 (#250), Qwen3.5 397B-A17B: 42.0 (#114)

BenchmarkMistralQwen3.5 397B-A17B
LMArena Coding11621465
LMArena WebDev—1400

Agentic & Tool Use Not comparable

Mistral: —, Qwen3.5 397B-A17B: 33.3 (#53)

BenchmarkMistralQwen3.5 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%

Reasoning Qwen3.5 397B-A17B leads

Mistral: 22.2 (#200), Qwen3.5 397B-A17B: 34.5 (#70)

BenchmarkMistralQwen3.5 397B-A17B
LMArena Hard Prompts11491448
Kagi LLM Benchmark—73.7%
NYT Connections (extended)—58.9%
Chess Puzzles—13%
Thematic Generalization—65.1%
Mystery Game Puzzles—18%
DTBench—87.5%
LMCA—37.9%
Epoch Capabilities Index—146.65

Math Qwen3.5 397B-A17B leads

Mistral: 22.3 (#278), Qwen3.5 397B-A17B: 46.1 (#73)

BenchmarkMistralQwen3.5 397B-A17B
LMArena Math11801454
FrontierMath (Tiers 1-3)—31.2%
OTIS Mock AIME 2024-2025—88.9%
Omni-MATH7.2%—

Knowledge Qwen3.5 397B-A17B leads

Mistral: 16.6 (#288), Qwen3.5 397B-A17B: 53.3 (#58)

BenchmarkMistralQwen3.5 397B-A17B
LMArena Expert11251462
GPQA Diamond—86.4%
MMLU-Pro27.7%—
GPQA (HELM)30.3%—

Multimodal Not comparable

Mistral: —, Qwen3.5 397B-A17B: 40.7 (#44)

BenchmarkMistralQwen3.5 397B-A17B
LMArena Vision—1263

Multilingual Qwen3.5 397B-A17B leads

Mistral: 32.8 (#254), Qwen3.5 397B-A17B: 53.7 (#59)

BenchmarkMistralQwen3.5 397B-A17B
LMArena Non-English11291430
LMArena Chinese11091500
LMArena French11801461
LMArena German11551447
LMArena Japanese10131426
LMArena Korean10321384
LMArena Russian11681429
LMArena Spanish11431441

Instruction Following Qwen3.5 397B-A17B leads

Mistral: 52.6 (#288), Qwen3.5 397B-A17B: 75.0 (#77)

BenchmarkMistralQwen3.5 397B-A17B
LMArena Instruction Following11521424
IFEval56.8%—

Long Context Qwen3.5 397B-A17B leads

Mistral: 35.0 (#245), Qwen3.5 397B-A17B: 44.1 (#74)

BenchmarkMistralQwen3.5 397B-A17B
LMArena Longer Query11531442

Writing & Preference Qwen3.5 397B-A17B leads

Mistral: 37.0 (#260), Qwen3.5 397B-A17B: 62.3 (#79)

BenchmarkMistralQwen3.5 397B-A17B
LMArena Text11651438
LMArena Creative Writing11581401
LMArena Multi-Turn11471446
EQ-Bench Creative Writing—1478
WildBench66%—

Frequently asked questions

Is Mistral better than Qwen3.5 397B-A17B?

Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 29.9 on the Noometry Index.

Is Mistral or Qwen3.5 397B-A17B better for coding?

Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 33.8 in the Noometry coding category.

How many benchmarks do Mistral and Qwen3.5 397B-A17B share?

17 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Qwen3.5 397B-A17B has 36.

Related comparisons

Go deeper