LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Mercury 2 vs Qwen3 Coder 480B A35B

Updated October 21, 2026. 36 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Mercury 2 Replace Qwen3 Coder 480B A35B
Mercury 2Inception
Coding
0.0
Overall
10.8
Output $/M
$0.75
12
Qwen3 Coder 480B A35BQwen
Coding
50.0
Overall
11.9
Output $/M
$1.00
24
vs boards won of 36 shared

Decision reading

Pick Qwen3 Coder 480B A35B for coding: it scores 50.0 on the Vibe Coding Index against 0.0 for Mercury 2.

Pick Mercury 2 when output tokens cost 1.3x less, or when what matters is Terminal-Bench Hard (Artificial Analysis run) or WeirdML, where it leads.

Model AMercury 2Inception0.0/1001 independent benchmarkNo cost per solved taskModel BQwen3 Coder 480B A35BQwen50.0/1002 independent benchmarksNo cost per solved task
Shared results
36
Mercury 2 only
6
Qwen3 Coder 480B A35B only
16
Like-for-like categories
7 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Mercury 2 0.0 from 1 benchmark, Qwen3 Coder 480B A35B 50.0 from 2 benchmarks.
Widest category
Agentic work, 27.2 points apart on average over 1 shared benchmark.
Widest single gap
IFBench: Mercury 2 69.8% against Qwen3 Coder 480B A35B 40.5%, 29.3 points apart on a 0 to 100 scale.
Output price
Mercury 2 $0.75 against Qwen3 Coder 480B A35B $1.00 per million output tokens, 1.3x apart.
Context window
Mercury 2 takes 128K tokens, Qwen3 Coder 480B A35B 262K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryMercury 2BarsQwen3 Coder 480B A35BTies
Coding35
Intelligence01
Agentic work10
Reasoning32
Knowledge21
Web design05
General310
All shared boards1224
CodingLike-for-likeFour of these boards feed the Vibe Coding Index35
Coding benchmarks for Mercury 2 and Qwen3 Coder 480B A35B
BenchmarkMercury 2Qwen3 Coder 480B A35BLeader
SWE-bench VerifiedNot measured69.6%Only Qwen3 Coder 480B A35B measured
LMArena WebDev11711275Qwen3 Coder 480B A35B
AA Coding Index31.1Not measuredOnly Mercury 2 measured
LiveCodeBench (Artificial Analysis run)Not measured58.5%Only Qwen3 Coder 480B A35B measured
SciCode37.7%Not measuredOnly Mercury 2 measured
Terminal-Bench Hard (Artificial Analysis run)26.5%18.9%Mercury 2
Terminal-BenchNot measured27.2%Only Qwen3 Coder 480B A35B measured
GSO-BenchNot measured4.9%Only Qwen3 Coder 480B A35B measured
WeirdML43.2%41.2%Mercury 2
ALE-Bench785.6461.4Mercury 2
LMArena Text: coding13901412Qwen3 Coder 480B A35B
LMArena Text: software and IT13851393Qwen3 Coder 480B A35B
LMArena WebDev: React11601257Qwen3 Coder 480B A35B
LMArena WebDev: HTML11991287Qwen3 Coder 480B A35B
Neither model has a result on the other 24 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Mercury 2 and Qwen3 Coder 480B A35B
BenchmarkMercury 2Qwen3 Coder 480B A35BLeader
AA Intelligence Index10.811.9Qwen3 Coder 480B A35B
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for Mercury 2 and Qwen3 Coder 480B A35B
BenchmarkMercury 2Qwen3 Coder 480B A35BLeader
AA Agentic Index1.6Not measuredOnly Mercury 2 measured
τ²-Bench Telecom70.8%43.6%Mercury 2
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index32
Reasoning benchmarks for Mercury 2 and Qwen3 Coder 480B A35B
BenchmarkMercury 2Qwen3 Coder 480B A35BLeader
GPQA Diamond (Artificial Analysis run)77.0%61.8%Mercury 2
Humanity's Last Exam (Artificial Analysis run)17.1%4.5%Mercury 2
LMArena Text: hard prompts13621372Qwen3 Coder 480B A35B
LMArena Text: expert13581338Mercury 2
LMArena Text: hard prompts in English13741380Qwen3 Coder 480B A35B
Neither model has a result on the other 16 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Math benchmarks for Mercury 2 and Qwen3 Coder 480B A35B
BenchmarkMercury 2Qwen3 Coder 480B A35BLeader
AA Math IndexNot measured39.3Only Qwen3 Coder 480B A35B measured
AIME 2025 (Artificial Analysis run)Not measured39.3%Only Qwen3 Coder 480B A35B measured
LMArena Text: mathNot measured1365Only Qwen3 Coder 480B A35B measured
LMArena Text: mathematical workNot measured1367Only Qwen3 Coder 480B A35B measured
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index21
Knowledge benchmarks for Mercury 2 and Qwen3 Coder 480B A35B
BenchmarkMercury 2Qwen3 Coder 480B A35BLeader
MMLU Pro (Artificial Analysis run)Not measured78.8%Only Qwen3 Coder 480B A35B measured
LMArena Text: science13431347Qwen3 Coder 480B A35B
LMArena Text: medicine and healthcare13631347Mercury 2
LMArena Text: legal and governmentNot measured1358Only Qwen3 Coder 480B A35B measured
LMArena Text: business and finance13491343Mercury 2
Neither model has a result on the other 12 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index05
Web design benchmarks for Mercury 2 and Qwen3 Coder 480B A35B
BenchmarkMercury 2Qwen3 Coder 480B A35BLeader
Design Arena: websites10361159Qwen3 Coder 480B A35B
Design Arena: UI components9981112Qwen3 Coder 480B A35B
Design Arena: game dev9851099Qwen3 Coder 480B A35B
Design Arena: data viz10091084Qwen3 Coder 480B A35B
Design Arena: 3D982Not measuredOnly Mercury 2 measured
Design Arena: all code categories10221143Qwen3 Coder 480B A35B
Design Arena: SVG998Not measuredOnly Mercury 2 measured
Design Arena: ASCII art990Not measuredOnly Mercury 2 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index310
General benchmarks for Mercury 2 and Qwen3 Coder 480B A35B
BenchmarkMercury 2Qwen3 Coder 480B A35BLeader
IFBench69.8%40.5%Mercury 2
Long context reasoning (AA-LCR)43.7%45.7%Qwen3 Coder 480B A35B
LMArena Text13541357Qwen3 Coder 480B A35B
LMArena Text: instruction following13281355Qwen3 Coder 480B A35B
LMArena Text: creative writing12861333Qwen3 Coder 480B A35B
LMArena Text: English13781359Mercury 2
LMArena Text: non-English13301346Qwen3 Coder 480B A35B
LMArena Text: Chinese14141357Mercury 2
LMArena Text: GermanNot measured1325Only Qwen3 Coder 480B A35B measured
LMArena Text: JapaneseNot measured1311Only Qwen3 Coder 480B A35B measured
LMArena Text: KoreanNot measured1305Only Qwen3 Coder 480B A35B measured
LMArena Text: FrenchNot measured1398Only Qwen3 Coder 480B A35B measured
LMArena Text: SpanishNot measured1360Only Qwen3 Coder 480B A35B measured
LMArena Text: Russian13041366Qwen3 Coder 480B A35B
LMArena Text: PolishNot measured1344Only Qwen3 Coder 480B A35B measured
LMArena Text: multi-turn13571366Qwen3 Coder 480B A35B
LMArena Text: longer queries13291378Qwen3 Coder 480B A35B
LMArena Text: writing and language13001340Qwen3 Coder 480B A35B
LMArena Text: entertainment and media13141317Qwen3 Coder 480B A35B
Neither model has a result on the other 27 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Mercury 2 and Qwen3 Coder 480B A35B
BenchmarkMercury 2Qwen3 Coder 480B A35BLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Mercury 2$0.0006Fits in one request
Qwen3 Coder 480B A35B$0.0008Fits in one request

Mercury 2 costs less

Repository review

50K input + 3K output tokens

Mercury 2$0.015Fits in one request
Qwen3 Coder 480B A35B$0.018Fits in one request

Mercury 2 costs less

Agent loop

200K input + 10K output tokens

Mercury 2$0.058Exceeds the context window
Qwen3 Coder 480B A35B$0.070Fits in one request

Mercury 2 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Mercury 2 and Qwen3 Coder 480B A35B
SpecificationInception Mercury 2Qwen3 Coder 480B A35B
MakerInceptionQwen
WeightsNo public weights listedOpen weights
ReleasedMarch 4, 2026July 23, 2025
Context window128K262K
Input $/Mtok$0.25$0.30
Output $/Mtok$0.75$1.00
Coding index0.050.0
Independent measurements behind it12
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Mercury 2 better than Qwen3 Coder 480B A35B for coding?

Pick Qwen3 Coder 480B A35B for coding: it scores 50.0 on the Vibe Coding Index against 0.0 for Mercury 2. Pick Mercury 2 when output tokens cost 1.3x less, or when what matters is Terminal-Bench Hard (Artificial Analysis run) or WeirdML, where it leads.

Which is cheaper, Mercury 2 or Qwen3 Coder 480B A35B?

Mercury 2 costs $0.25 per million input tokens and $0.75 per million output tokens; Qwen3 Coder 480B A35B costs $0.30 and $1.00. Cost per solved task is known for neither of them.

Which has the bigger context window, Mercury 2 or Qwen3 Coder 480B A35B?

Qwen3 Coder 480B A35B, with 262K tokens against 128K.

How many benchmarks is the Mercury 2 vs Qwen3 Coder 480B A35B comparison based on?

36 benchmarks have a result for both models as of October 21, 2026. Mercury 2's coding index rests on 1 independent benchmark and Qwen3 Coder 480B A35B's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next