Model comparison

Mercury 2.5 vs Qwen3.5 35B-A3B

Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 33.5 on the Noometry Index. Mercury 2.5 costs 10× less per token, which makes it the better buy when Qwen3.5 35B-A3B's lead doesn't matter for your workload.

Last verified October 10, 2026. 2 shared benchmarks.

Mercury 2.5 Inception

33.5

Rank #242 Reported

Qwen3.5 35B-A3B

Alibaba (Qwen)

42.0

Rank #123 Confirmed

Summary

They share 2 benchmarks with published results for both. Mercury 2.5 scores higher in 1 category and Qwen3.5 35B-A3B in 2 categories; 3 gaps are clear of the uncertainty.
The widest gap is in math, where Qwen3.5 35B-A3B leads 39.9 to 23.3.
The biggest single-benchmark swing is SciCode: 38.5% for Mercury 2.5 and 29.3% for Qwen3.5 35B-A3B.
Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $0.25 / $2 for Qwen3.5 35B-A3B.
Qwen3.5 35B-A3B accepts more context: 262K tokens versus 260K.
Qwen3.5 35B-A3B has downloadable open weights; the other is API-only.

Side by side

Mercury 2.5 and Qwen3.5 35B-A3B specifications
	Mercury 2.5	Qwen3.5 35B-A3B
Provider	Inception	Alibaba (Qwen)
Noometry Index	33.5	42.0
Released	2026-09-08	2026-02-01
Weights	Proprietary	Open
Context window	260K	262K
Max output	66K	66K
Input $ / M tokens	$0.04	$0.25
Output $ / M tokens	$0.15	$2
Results tracked	4	28

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

Category by category

Coding Mercury 2.5 leads

Mercury 2.5: 39.5 (#156), Qwen3.5 35B-A3B: 33.8 (#251)

Coding benchmarks
Benchmark	Mercury 2.5	Qwen3.5 35B-A3B
SciCode	38.5%	29.3%
LMArena WebDev	—	1254
LMArena Coding	—	1410
ALE-Bench	301.65	—

Reasoning Qwen3.5 35B-A3B leads

Mercury 2.5: 22.4 (#193), Qwen3.5 35B-A3B: 24.6 (#161)

Reasoning benchmarks
Benchmark	Mercury 2.5	Qwen3.5 35B-A3B
CritPt	0%	0.6%
Chess Puzzles	—	10%
LMArena Hard Prompts	—	1400
DTBench	—	80%
LMCA	—	29.5%
Epoch Capabilities Index	—	142.52

Math Qwen3.5 35B-A3B leads

Mercury 2.5: 23.3 (#272), Qwen3.5 35B-A3B: 39.9 (#97)

Math benchmarks
Benchmark	Mercury 2.5	Qwen3.5 35B-A3B
MathArena Final-Answer Competitions	—	56%
OTIS Mock AIME 2024-2025	—	70%
ProofBench	3%	—
LMArena Math	—	1404

Knowledge Not comparable

Mercury 2.5: —, Qwen3.5 35B-A3B: 47.8 (#79)

Knowledge benchmarks
Benchmark	Mercury 2.5	Qwen3.5 35B-A3B
GPQA Diamond	—	83.5%
Vectara Hallucination Rate	—	10.5%
LMArena Expert	—	1408

Multilingual Not comparable

Mercury 2.5: —, Qwen3.5 35B-A3B: 50.0 (#127)

Multilingual benchmarks
Benchmark	Mercury 2.5	Qwen3.5 35B-A3B
LMArena Non-English	—	1378
LMArena Chinese	—	1457
LMArena French	—	1412
LMArena German	—	1367
LMArena Japanese	—	1325
LMArena Korean	—	1356
LMArena Russian	—	1376
LMArena Spanish	—	1392

Instruction Following Not comparable

Mercury 2.5: —, Qwen3.5 35B-A3B: 72.8 (#128)

Instruction Following benchmarks
Benchmark	Mercury 2.5	Qwen3.5 35B-A3B
LMArena Instruction Following	—	1379

Long Context Not comparable

Mercury 2.5: —, Qwen3.5 35B-A3B: 42.4 (#127)

Long Context benchmarks
Benchmark	Mercury 2.5	Qwen3.5 35B-A3B
LMArena Longer Query	—	1389

Writing & Preference Not comparable

Mercury 2.5: —, Qwen3.5 35B-A3B: 57.9 (#124)

Writing & Preference benchmarks
Benchmark	Mercury 2.5	Qwen3.5 35B-A3B
LMArena Text	—	1395
LMArena Creative Writing	—	1346
LMArena Multi-Turn	—	1390

Frequently asked questions

Is Mercury 2.5 better than Qwen3.5 35B-A3B?

Which is cheaper, Mercury 2.5 or Qwen3.5 35B-A3B?

Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; Qwen3.5 35B-A3B lists at $0.25 and $2.

Is Mercury 2.5 or Qwen3.5 35B-A3B better for coding?

Mercury 2.5 scores higher on coding benchmarks: 39.5 versus 33.8 in the Noometry coding category.

Which has the bigger context window?

Qwen3.5 35B-A3B does, with 262K tokens against 260K.

How many benchmarks do Mercury 2.5 and Qwen3.5 35B-A3B share?

2 benchmarks have published results for both models. Mercury 2.5 has 4 scored results on Noometry and Qwen3.5 35B-A3B has 28.