Noometry

Model comparison

Mercury 2 vs Qwen3.5-Flash

Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 39.1 on the Noometry Index.

Last verified . 14 shared benchmarks.

Mercury 2 Inception

39.1

Rank #175 Confirmed

Qwen3.5-Flash Alibaba (Qwen)

42.5

Rank #112 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Mercury 2 scores higher in 0 categories and Qwen3.5-Flash in 7 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Qwen3.5-Flash leads 33.7 to 23.8.
  • Qwen3.5-Flash is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
  • Qwen3.5-Flash accepts more context: 1M tokens versus 128K.

Side by side

Mercury 2Qwen3.5-Flash
ProviderInceptionAlibaba (Qwen)
Noometry Index39.142.5
Released2026-02-202026-02-23
WeightsProprietaryProprietary
Context window128K1M
Max output50K66K
Input $ / M tokens$0.25$0.10
Output $ / M tokens$0.75$0.40
Results tracked1732

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

Category by category

Coding Too close to call

Mercury 2: 33.5 (#255), Qwen3.5-Flash: 34.2 (#242)

BenchmarkMercury 2Qwen3.5-Flash
LMArena WebDev11711244
LMArena Coding13911412
ALE-Bench785.58221.8
SciCode38.7%—
WeirdML43.2%—

Agentic & Tool Use Not comparable

Mercury 2: —, Qwen3.5-Flash: —

BenchmarkMercury 2Qwen3.5-Flash
Vending-Bench 2—462.69

Reasoning Qwen3.5-Flash leads

Mercury 2: 23.8 (#170), Qwen3.5-Flash: 33.7 (#72)

BenchmarkMercury 2Qwen3.5-Flash
LMArena Hard Prompts13621403
CritPt0.8%—
Chess Puzzles—21%
Mystery Game Puzzles—20%
DTBench—82.9%
LMCA—29.1%
Epoch Capabilities Index—143.98

Math Not comparable

Mercury 2: —, Qwen3.5-Flash: 37.4 (#158)

BenchmarkMercury 2Qwen3.5-Flash
FrontierMath (Tiers 1-3)—18.2%
OTIS Mock AIME 2024-2025—84.4%
LMArena Math—1407
FrontierMath (Feb 2025 set)—6.2%
FrontierMath Tier 4 (v1)—0%

Knowledge Qwen3.5-Flash leads

Mercury 2: 36.2 (#172), Qwen3.5-Flash: 43.2 (#93)

BenchmarkMercury 2Qwen3.5-Flash
Vectara Hallucination Rate12.3%10.5%
LMArena Expert13581407
GPQA Diamond—82.3%
SimpleQA Verified—20.3%

Multilingual Qwen3.5-Flash leads

Mercury 2: 46.6 (#157), Qwen3.5-Flash: 50.5 (#121)

BenchmarkMercury 2Qwen3.5-Flash
LMArena Non-English13311385
LMArena Chinese14171446
LMArena Russian13041379
LMArena French—1412
LMArena German—1390
LMArena Japanese—1368
LMArena Korean—1344
LMArena Spanish—1400

Instruction Following Qwen3.5-Flash leads

Mercury 2: 70.2 (#165), Qwen3.5-Flash: 72.6 (#139)

BenchmarkMercury 2Qwen3.5-Flash
LMArena Instruction Following13291374

Long Context Qwen3.5-Flash leads

Mercury 2: 40.5 (#154), Qwen3.5-Flash: 42.4 (#124)

BenchmarkMercury 2Qwen3.5-Flash
LMArena Longer Query13301392

Writing & Preference Qwen3.5-Flash leads

Mercury 2: 53.8 (#155), Qwen3.5-Flash: 57.9 (#122)

BenchmarkMercury 2Qwen3.5-Flash
LMArena Text13551397
LMArena Creative Writing12891343
LMArena Multi-Turn13581393

Frequently asked questions

Is Mercury 2 better than Qwen3.5-Flash?

Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 39.1 on the Noometry Index.

Which is cheaper, Mercury 2 or Qwen3.5-Flash?

Qwen3.5-Flash is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Mercury 2 lists at $0.25 and $0.75.

Is Mercury 2 or Qwen3.5-Flash better for coding?

They score almost the same on coding (33.5 vs 34.2); test both on your own repository before choosing.

Which has the bigger context window?

Qwen3.5-Flash does, with 1M tokens against 128K.

How many benchmarks do Mercury 2 and Qwen3.5-Flash share?

14 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Qwen3.5-Flash has 32.

Related comparisons

Go deeper