Noometry

Model comparison

Mercury 2 vs Qwen3.5 35B-A3B

Qwen3.5 35B-A3B is the stronger model overall, scoring 41.7 to 38.8 on the Noometry Index. Mercury 2 costs 1.8× less per token, which makes it the better buy when Qwen3.5 35B-A3B's lead doesn't matter for your workload.

Last verified . 15 shared benchmarks.

Mercury 2 Inception

38.8

Rank #167 Confirmed

Qwen3.5 35B-A3B Alibaba (Qwen)

41.7

Rank #118 Confirmed

Summary

  • They share 15 benchmarks with published results for both. Mercury 2 scores higher in 0 categories and Qwen3.5 35B-A3B in 7 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3.5 35B-A3B leads 47.7 to 35.6.
  • The biggest single-benchmark swing is SciCode: 38.7% for Mercury 2 and 29.3% for Qwen3.5 35B-A3B.
  • Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.25 / $2 for Qwen3.5 35B-A3B.
  • Qwen3.5 35B-A3B accepts more context: 262K tokens versus 128K.
  • Qwen3.5 35B-A3B has downloadable open weights; the other is API-only.

Side by side

Mercury 2Qwen3.5 35B-A3B
ProviderInceptionAlibaba (Qwen)
Noometry Index38.841.7
Released2026-02-202026-02-01
WeightsProprietaryOpen
Context window128K262K
Max output50K66K
Input $ / M tokens$0.25$0.25
Output $ / M tokens$0.75$2
Results tracked1728

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

Category by category

Coding Too close to call

Mercury 2: 33.2 (#250), Qwen3.5 35B-A3B: 33.5 (#244)

BenchmarkMercury 2Qwen3.5 35B-A3B
LMArena WebDev11701254
SciCode38.7%29.3%
LMArena Coding13911410
WeirdML43.2%—
ALE-Bench785.58—

Reasoning Too close to call

Mercury 2: 23.0 (#170), Qwen3.5 35B-A3B: 23.9 (#158)

BenchmarkMercury 2Qwen3.5 35B-A3B
CritPt0.8%0.6%
LMArena Hard Prompts13621400
Chess Puzzles—10%
DTBench—80%
LMCA—29.5%
Epoch Capabilities Index—142.52

Math Not comparable

Mercury 2: —, Qwen3.5 35B-A3B: 38.4 (#86)

BenchmarkMercury 2Qwen3.5 35B-A3B
MathArena Final-Answer Competitions—56%
OTIS Mock AIME 2024-2025—70%
LMArena Math—1404

Knowledge Qwen3.5 35B-A3B leads

Mercury 2: 35.6 (#170), Qwen3.5 35B-A3B: 47.7 (#73)

BenchmarkMercury 2Qwen3.5 35B-A3B
Vectara Hallucination Rate12.3%10.5%
LMArena Expert13581408
GPQA Diamond—83.5%

Multilingual Qwen3.5 35B-A3B leads

Mercury 2: 46.8 (#153), Qwen3.5 35B-A3B: 50.2 (#122)

BenchmarkMercury 2Qwen3.5 35B-A3B
LMArena Non-English13311379
LMArena Chinese14161458
LMArena Russian13031377
LMArena French—1412
LMArena German—1367
LMArena Japanese—1326
LMArena Korean—1354
LMArena Spanish—1390

Instruction Following Qwen3.5 35B-A3B leads

Mercury 2: 70.4 (#161), Qwen3.5 35B-A3B: 73.0 (#123)

BenchmarkMercury 2Qwen3.5 35B-A3B
LMArena Instruction Following13281379

Long Context Qwen3.5 35B-A3B leads

Mercury 2: 40.4 (#149), Qwen3.5 35B-A3B: 42.4 (#122)

BenchmarkMercury 2Qwen3.5 35B-A3B
LMArena Longer Query13291390

Writing & Preference Qwen3.5 35B-A3B leads

Mercury 2: 54.0 (#151), Qwen3.5 35B-A3B: 58.1 (#118)

BenchmarkMercury 2Qwen3.5 35B-A3B
LMArena Text13551395
LMArena Creative Writing12891347
LMArena Multi-Turn13581391

Frequently asked questions

Is Mercury 2 better than Qwen3.5 35B-A3B?

Qwen3.5 35B-A3B is the stronger model overall, scoring 41.7 to 38.8 on the Noometry Index. Mercury 2 costs 1.8× less per token, which makes it the better buy when Qwen3.5 35B-A3B's lead doesn't matter for your workload.

Which is cheaper, Mercury 2 or Qwen3.5 35B-A3B?

Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Qwen3.5 35B-A3B lists at $0.25 and $2.

Is Mercury 2 or Qwen3.5 35B-A3B better for coding?

They score almost the same on coding (33.2 vs 33.5); test both on your own repository before choosing.

Which has the bigger context window?

Qwen3.5 35B-A3B does, with 262K tokens against 128K.

How many benchmarks do Mercury 2 and Qwen3.5 35B-A3B share?

15 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Qwen3.5 35B-A3B has 28.

Related comparisons

Go deeper