Model comparison

Mercury 2 vs Qwen3.6 35B-A3B

Mercury 2 is the stronger model overall, scoring 38.8 to 37.2 on the Noometry Index.

Last verified October 10, 2026. 3 shared benchmarks.

Mercury 2 Inception

38.8

Rank #167 Confirmed

Qwen3.6 35B-A3B

Alibaba (Qwen)

37.2

Rank #194 Confirmed

Summary

They share 3 benchmarks with published results for both. Mercury 2 scores higher in 0 categories and Qwen3.6 35B-A3B in 3 categories; 3 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Qwen3.6 35B-A3B leads 51.4 to 35.6.
The biggest single-benchmark swing is WeirdML: 43.2% for Mercury 2 and 34.5% for Qwen3.6 35B-A3B.
Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.25 / $1.49 for Qwen3.6 35B-A3B.
Qwen3.6 35B-A3B accepts more context: 262K tokens versus 128K.
Qwen3.6 35B-A3B has downloadable open weights; the other is API-only.

Side by side

Mercury 2 and Qwen3.6 35B-A3B specifications
	Mercury 2	Qwen3.6 35B-A3B
Provider	Inception	Alibaba (Qwen)
Noometry Index	38.8	37.2
Released	2026-02-20	2026-04-01
Weights	Proprietary	Open
Context window	128K	262K
Max output	50K	66K
Input $ / M tokens	$0.25	$0.25
Output $ / M tokens	$0.75	$1.49
Results tracked	17	14

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

Category by category

Coding Qwen3.6 35B-A3B leads

Mercury 2: 33.2 (#250), Qwen3.6 35B-A3B: 36.7 (#190)

Coding benchmarks
Benchmark	Mercury 2	Qwen3.6 35B-A3B
SciCode	38.7%	35.8%
WeirdML	43.2%	34.5%
LMArena WebDev	1170	—
LMArena Coding	1391	—
ALE-Bench	785.58	—

Agentic & Tool Use Not comparable

Mercury 2: —, Qwen3.6 35B-A3B: 21.9 (#126)

Agentic & Tool Use benchmarks
Benchmark	Mercury 2	Qwen3.6 35B-A3B
Terminal-Bench	—	23%

Reasoning Qwen3.6 35B-A3B leads

Mercury 2: 23.0 (#170), Qwen3.6 35B-A3B: 27.2 (#112)

Reasoning benchmarks
Benchmark	Mercury 2	Qwen3.6 35B-A3B
CritPt	0.8%	0.3%
NYT Connections (extended)	—	41.6%
Chess Puzzles	—	26%
LMArena Hard Prompts	1362	—
Mystery Game Puzzles	—	22%
DTBench	—	73.9%
LMCA	—	29.7%
Surface Evolver Bench	—	44.4%
Epoch Capabilities Index	—	143.92

Math Not comparable

Mercury 2: —, Qwen3.6 35B-A3B: 37.9 (#90)

Math benchmarks
Benchmark	Mercury 2	Qwen3.6 35B-A3B
FrontierMath (Tiers 1-3)	—	20.4%
OTIS Mock AIME 2024-2025	—	86.7%

Knowledge Qwen3.6 35B-A3B leads

Mercury 2: 35.6 (#170), Qwen3.6 35B-A3B: 51.4 (#63)

Knowledge benchmarks
Benchmark	Mercury 2	Qwen3.6 35B-A3B
GPQA Diamond	—	84.8%
Vectara Hallucination Rate	12.3%	—
LMArena Expert	1358	—

Multilingual Not comparable

Mercury 2: 46.8 (#153), Qwen3.6 35B-A3B: —

Multilingual benchmarks
Benchmark	Mercury 2	Qwen3.6 35B-A3B
LMArena Non-English	1331	—
LMArena Chinese	1416	—
LMArena Russian	1303	—

Instruction Following Not comparable

Mercury 2: 70.4 (#161), Qwen3.6 35B-A3B: —

Instruction Following benchmarks
Benchmark	Mercury 2	Qwen3.6 35B-A3B
LMArena Instruction Following	1328	—

Long Context Not comparable

Mercury 2: 40.4 (#149), Qwen3.6 35B-A3B: —

Long Context benchmarks
Benchmark	Mercury 2	Qwen3.6 35B-A3B
LMArena Longer Query	1329	—

Writing & Preference Not comparable

Mercury 2: 54.0 (#151), Qwen3.6 35B-A3B: —

Writing & Preference benchmarks
Benchmark	Mercury 2	Qwen3.6 35B-A3B
LMArena Text	1355	—
LMArena Creative Writing	1289	—
LMArena Multi-Turn	1358	—

Frequently asked questions

Is Mercury 2 better than Qwen3.6 35B-A3B?

Mercury 2 is the stronger model overall, scoring 38.8 to 37.2 on the Noometry Index.

Which is cheaper, Mercury 2 or Qwen3.6 35B-A3B?

Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Qwen3.6 35B-A3B lists at $0.25 and $1.49.

Is Mercury 2 or Qwen3.6 35B-A3B better for coding?

Qwen3.6 35B-A3B scores higher on coding benchmarks: 36.7 versus 33.2 in the Noometry coding category.

Which has the bigger context window?

Qwen3.6 35B-A3B does, with 262K tokens against 128K.

How many benchmarks do Mercury 2 and Qwen3.6 35B-A3B share?

3 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Qwen3.6 35B-A3B has 14.