Noometry

Model comparison

MiniMax-M2.7 vs Qwen3.5 35B-A3B

Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 37.7 on the Noometry Index.

Last verified . 22 shared benchmarks.

MiniMax-M2.7 MiniMax

37.7

Rank #196 Confirmed

Qwen3.5 35B-A3B Alibaba (Qwen)

42.0

Rank #123 Confirmed

Summary

  • They share 22 benchmarks with published results for both. MiniMax-M2.7 scores higher in 5 categories and Qwen3.5 35B-A3B in 3 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.5 35B-A3B leads 39.9 to 25.9.
  • The biggest single-benchmark swing is SciCode: 47% for MiniMax-M2.7 and 29.3% for Qwen3.5 35B-A3B.
  • MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.25 / $2 for Qwen3.5 35B-A3B.
  • Qwen3.5 35B-A3B accepts more context: 262K tokens versus 205K.

Side by side

MiniMax-M2.7Qwen3.5 35B-A3B
ProviderMiniMaxAlibaba (Qwen)
Noometry Index37.742.0
Released2026-03-182026-02-01
WeightsOpenOpen
Context window205K262K
Max output131K66K
Input $ / M tokens$0.30$0.25
Output $ / M tokens$1.20$2
Results tracked3028

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

Category by category

Coding MiniMax-M2.7 leads

MiniMax-M2.7: 41.8 (#120), Qwen3.5 35B-A3B: 33.8 (#251)

BenchmarkMiniMax-M2.7Qwen3.5 35B-A3B
LMArena WebDev13981254
SciCode47%29.3%
LMArena Coding14541410
WeirdML37%—
ALE-Bench599.25—

Agentic & Tool Use Not comparable

MiniMax-M2.7: 25.1 (#111), Qwen3.5 35B-A3B: —

BenchmarkMiniMax-M2.7Qwen3.5 35B-A3B
Terminal-Bench45.1%—
ExploitBench13.3%—
GBAEval0%—

Reasoning Qwen3.5 35B-A3B leads

MiniMax-M2.7: 19.7 (#253), Qwen3.5 35B-A3B: 24.6 (#161)

BenchmarkMiniMax-M2.7Qwen3.5 35B-A3B
CritPt0.6%0.6%
LMArena Hard Prompts14221400
Epoch Capabilities Index145.85142.52
NYT Connections (extended)24.7%—
Chess Puzzles—10%
Thematic Generalization39.3%—
DTBench—80%
LMCA—29.5%

Math Qwen3.5 35B-A3B leads

MiniMax-M2.7: 25.9 (#263), Qwen3.5 35B-A3B: 39.9 (#97)

BenchmarkMiniMax-M2.7Qwen3.5 35B-A3B
LMArena Math14201404
MathArena Final-Answer Competitions—56%
OTIS Mock AIME 2024-2025—70%
ProofBench3%—

Knowledge Qwen3.5 35B-A3B leads

MiniMax-M2.7: 37.7 (#152), Qwen3.5 35B-A3B: 47.8 (#79)

BenchmarkMiniMax-M2.7Qwen3.5 35B-A3B
Vectara Hallucination Rate12.9%10.5%
LMArena Expert14441408
GPQA Diamond—83.5%

Multilingual Too close to call

MiniMax-M2.7: 50.3 (#123), Qwen3.5 35B-A3B: 50.0 (#127)

BenchmarkMiniMax-M2.7Qwen3.5 35B-A3B
LMArena Non-English13821378
LMArena Chinese14411457
LMArena French14211412
LMArena German13981367
LMArena Japanese12621325
LMArena Korean13131356
LMArena Russian13831376
LMArena Spanish14031392

Instruction Following MiniMax-M2.7 leads

MiniMax-M2.7: 74.1 (#103), Qwen3.5 35B-A3B: 72.8 (#128)

BenchmarkMiniMax-M2.7Qwen3.5 35B-A3B
LMArena Instruction Following14051379

Long Context Too close to call

MiniMax-M2.7: 43.3 (#99), Qwen3.5 35B-A3B: 42.4 (#127)

BenchmarkMiniMax-M2.7Qwen3.5 35B-A3B
LMArena Longer Query14191389

Writing & Preference MiniMax-M2.7 leads

MiniMax-M2.7: 58.9 (#112), Qwen3.5 35B-A3B: 57.9 (#124)

BenchmarkMiniMax-M2.7Qwen3.5 35B-A3B
LMArena Text14051395
LMArena Creative Writing13541346
LMArena Multi-Turn14121390

Frequently asked questions

Is MiniMax-M2.7 better than Qwen3.5 35B-A3B?

Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 37.7 on the Noometry Index.

Which is cheaper, MiniMax-M2.7 or Qwen3.5 35B-A3B?

MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen3.5 35B-A3B lists at $0.25 and $2.

Is MiniMax-M2.7 or Qwen3.5 35B-A3B better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 33.8 in the Noometry coding category.

Which has the bigger context window?

Qwen3.5 35B-A3B does, with 262K tokens against 205K.

How many benchmarks do MiniMax-M2.7 and Qwen3.5 35B-A3B share?

22 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Qwen3.5 35B-A3B has 28.

Related comparisons

Go deeper