Enter opens the highlighted result. Esc closes.

Claude Sonnet 4.5 vs Mercury 2

Updated October 21, 2026. 34 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Sonnet 4.5 Replace Mercury 2
Claude Sonnet 4.5Anthropic
Coding
59.1
Overall
20.7
Output $/M
$15.00
34
Mercury 2Inception
Coding
0.0
Overall
10.8
Output $/M
$0.75
0
vs boards won of 34 shared

Decision reading

Pick Claude Sonnet 4.5 for coding: it scores 59.1 on the Vibe Coding Index against 0.0 for Mercury 2.

Pick Mercury 2 when output tokens cost 20.0x less.

Model AClaude Sonnet 4.5Anthropic59.1/1002 independent benchmarks$1.16 per solved taskModel BMercury 2Inception0.0/1001 independent benchmarkNo cost per solved task
Shared results
34
Claude Sonnet 4.5 only
58
Mercury 2 only
8
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
Claude Sonnet 4.5 59.1 from 2 benchmarks, Mercury 2 0.0 from 1 benchmark.
Widest category
Coding, 22.2 points apart on average over 7 shared benchmarks.
Widest single gap
LMArena WebDev: React: Claude Sonnet 4.5 1386 against Mercury 2 1160, 37.7 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 4.5 $15.00 against Mercury 2 $0.75 per million output tokens, 20.0x apart.
Context window
Claude Sonnet 4.5 takes 1M tokens, Mercury 2 128K.

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
CategoryClaude Sonnet 4.5BarsMercury 2Ties
Coding70
Intelligence10
Agentic work10
Reasoning30
Knowledge30
Web design80
General110
All shared boards340
CodingLike-for-likeFour of these boards feed the Vibe Coding Index70
Coding benchmarks for Claude Sonnet 4.5 and Mercury 2
BenchmarkClaude Sonnet 4.5Mercury 2Leader
SWE-bench Verified74.8%Not measuredOnly Claude Sonnet 4.5 measured
SWE-bench Multilingual67.0%Not measuredOnly Claude Sonnet 4.5 measured
LMArena WebDev13941171Claude Sonnet 4.5
AA Coding Index52.131.1Claude Sonnet 4.5
LiveCodeBench (Vals AI)73.0%Not measuredOnly Claude Sonnet 4.5 measured
SWE-bench Verified (Vals AI)70.0%Not measuredOnly Claude Sonnet 4.5 measured
Vibe Code Bench (Vals AI)22.6%Not measuredOnly Claude Sonnet 4.5 measured
SciCodeNot measured37.7%Only Mercury 2 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured26.5%Only Mercury 2 measured
Terminal-Bench46.5%Not measuredOnly Claude Sonnet 4.5 measured
GSO-Bench14.7%Not measuredOnly Claude Sonnet 4.5 measured
WeirdML47.7%43.2%Claude Sonnet 4.5
Cybench60.0%Not measuredOnly Claude Sonnet 4.5 measured
ALE-BenchNot measured785.6Only Mercury 2 measured
LMArena Text: coding14881390Claude Sonnet 4.5
LMArena Text: software and IT14731385Claude Sonnet 4.5
LMArena WebDev: React13861160Claude Sonnet 4.5
LMArena WebDev: HTML13991199Claude Sonnet 4.5
Neither model has a result on the other 20 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Claude Sonnet 4.5 and Mercury 2
BenchmarkClaude Sonnet 4.5Mercury 2Leader
AA Intelligence Index20.710.8Claude Sonnet 4.5
Epoch Capabilities Index146.7Not measuredOnly Claude Sonnet 4.5 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for Claude Sonnet 4.5 and Mercury 2
BenchmarkClaude Sonnet 4.5Mercury 2Leader
AA Agentic Index15.81.6Claude Sonnet 4.5
Design Arena: agents building web apps1060Not measuredOnly Claude Sonnet 4.5 measured
Design Arena: agents building full-stack apps1050Not measuredOnly Claude Sonnet 4.5 measured
Design Arena: agents building mobile apps1137Not measuredOnly Claude Sonnet 4.5 measured
τ²-Bench TelecomNot measured70.8%Only Mercury 2 measured
METR time horizons67.4%Not measuredOnly Claude Sonnet 4.5 measured
Remote Labor Index2.1%Not measuredOnly Claude Sonnet 4.5 measured
GDPval42.5%Not measuredOnly Claude Sonnet 4.5 measured
DeepResearch Bench52.6%Not measuredOnly Claude Sonnet 4.5 measured
OSWorld62.9%Not measuredOnly Claude Sonnet 4.5 measured
Vending-Bench 2$3,839Not measuredOnly Claude Sonnet 4.5 measured
Neither model has a result on the other 28 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
Reasoning benchmarks for Claude Sonnet 4.5 and Mercury 2
BenchmarkClaude Sonnet 4.5Mercury 2Leader
GPQA Diamond81.6%Not measuredOnly Claude Sonnet 4.5 measured
MMMU Pro (Vals AI)79.3%Not measuredOnly Claude Sonnet 4.5 measured
GPQA Diamond (Artificial Analysis run)Not measured77.0%Only Mercury 2 measured
Humanity's Last Exam (Artificial Analysis run)Not measured17.1%Only Mercury 2 measured
GPQA Diamond (Epoch AI run)82.3%Not measuredOnly Claude Sonnet 4.5 measured
ARC-AGI63.7%Not measuredOnly Claude Sonnet 4.5 measured
ARC-AGI-213.6%Not measuredOnly Claude Sonnet 4.5 measured
SimpleBench54.3%Not measuredOnly Claude Sonnet 4.5 measured
Chess puzzles10.0%Not measuredOnly Claude Sonnet 4.5 measured
Mystery game puzzles17.0%Not measuredOnly Claude Sonnet 4.5 measured
EBR-bench2.4%Not measuredOnly Claude Sonnet 4.5 measured
VPCT39.8%Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: hard prompts14621362Claude Sonnet 4.5
LMArena Text: expert14831358Claude Sonnet 4.5
LMArena Text: hard prompts in English14711374Claude Sonnet 4.5
Neither model has a result on the other 6 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Math benchmarks for Claude Sonnet 4.5 and Mercury 2
BenchmarkClaude Sonnet 4.5Mercury 2Leader
AIME88.2%Not measuredOnly Claude Sonnet 4.5 measured
MGSM (Vals AI)94.3%Not measuredOnly Claude Sonnet 4.5 measured
OTIS Mock AIME77.8%Not measuredOnly Claude Sonnet 4.5 measured
FrontierMath, tiers 1 to 323.9%Not measuredOnly Claude Sonnet 4.5 measured
FrontierMath, tier 42.4%Not measuredOnly Claude Sonnet 4.5 measured
ProofBench19.0%Not measuredOnly Claude Sonnet 4.5 measured
MATH level 597.7%Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: math1449Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: mathematical work1462Not measuredOnly Claude Sonnet 4.5 measured
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index30
Knowledge benchmarks for Claude Sonnet 4.5 and Mercury 2
BenchmarkClaude Sonnet 4.5Mercury 2Leader
MMLU Pro87.4%Not measuredOnly Claude Sonnet 4.5 measured
LegalBench (Vals AI)84.1%Not measuredOnly Claude Sonnet 4.5 measured
CaseLaw (Vals AI)62.2%Not measuredOnly Claude Sonnet 4.5 measured
CorpFin (Vals AI)62.0%Not measuredOnly Claude Sonnet 4.5 measured
TaxEval (Vals AI)73.3%Not measuredOnly Claude Sonnet 4.5 measured
MortgageTax (Vals AI)64.0%Not measuredOnly Claude Sonnet 4.5 measured
MedQA (Vals AI)94.7%Not measuredOnly Claude Sonnet 4.5 measured
MedCode (Vals AI)44.1%Not measuredOnly Claude Sonnet 4.5 measured
SimpleQA Verified30.7%Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: science14481343Claude Sonnet 4.5
LMArena Text: medicine and healthcare14441363Claude Sonnet 4.5
LMArena Text: legal and government1451Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: business and finance14401349Claude Sonnet 4.5
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for Claude Sonnet 4.5 and Mercury 2
BenchmarkClaude Sonnet 4.5Mercury 2Leader
Design Arena: websites11901036Claude Sonnet 4.5
Design Arena: UI components1173998Claude Sonnet 4.5
Design Arena: game dev1166985Claude Sonnet 4.5
Design Arena: data viz11671009Claude Sonnet 4.5
Design Arena: 3D1158982Claude Sonnet 4.5
Design Arena: all code categories11831022Claude Sonnet 4.5
Design Arena: SVG1114998Claude Sonnet 4.5
Design Arena: ASCII art1204990Claude Sonnet 4.5
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index110
General benchmarks for Claude Sonnet 4.5 and Mercury 2
BenchmarkClaude Sonnet 4.5Mercury 2Leader
SAGE (Vals AI)36.1%Not measuredOnly Claude Sonnet 4.5 measured
MedScribe (Vals AI)84.5%Not measuredOnly Claude Sonnet 4.5 measured
IFBenchNot measured69.8%Only Mercury 2 measured
Long context reasoning (AA-LCR)Not measured43.7%Only Mercury 2 measured
DTBench83.2%Not measuredOnly Claude Sonnet 4.5 measured
LMCA38.8%Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text14381354Claude Sonnet 4.5
LMArena Text: instruction following14591328Claude Sonnet 4.5
LMArena Text: creative writing14421286Claude Sonnet 4.5
LMArena Text: English14501378Claude Sonnet 4.5
LMArena Text: non-English14251330Claude Sonnet 4.5
LMArena Text: Chinese14601414Claude Sonnet 4.5
LMArena Text: German1427Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: Japanese1390Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: Korean1402Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: French1459Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: Spanish1458Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: Russian14371304Claude Sonnet 4.5
LMArena Text: Polish1423Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: multi-turn14651357Claude Sonnet 4.5
LMArena Text: longer queries14751329Claude Sonnet 4.5
LMArena Text: writing and language14421300Claude Sonnet 4.5
LMArena Text: entertainment and media14281314Claude Sonnet 4.5
LMArena Document1450Not measuredOnly Claude Sonnet 4.5 measured
Neither model has a result on the other 22 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Sonnet 4.5 and Mercury 2
BenchmarkClaude Sonnet 4.5Mercury 2Leader
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

Claude Sonnet 4.5$0.011Fits in one request
Mercury 2$0.0006Fits in one request

Mercury 2 costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 4.5$0.195Fits in one request
Mercury 2$0.015Fits in one request

Mercury 2 costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 4.5$0.750Fits in one request
Mercury 2$0.058Exceeds the context window

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 Claude Sonnet 4.5 and Mercury 2
SpecificationAnthropic Claude Sonnet 4.5Inception Mercury 2
MakerAnthropicInception
WeightsNo public weights listedNo public weights listed
ReleasedSeptember 29, 2025March 4, 2026
Context window1M128K
Input $/Mtok$3.00$0.25
Output $/Mtok$15.00$0.75
Coding index59.10.0
Independent measurements behind it21
Cost per solved task$1.16Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 4.5 better than Mercury 2 for coding?

Pick Claude Sonnet 4.5 for coding: it scores 59.1 on the Vibe Coding Index against 0.0 for Mercury 2. Pick Mercury 2 when output tokens cost 20.0x less.

Which is cheaper, Claude Sonnet 4.5 or Mercury 2?

Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; Mercury 2 costs $0.25 and $0.75. Cost per solved task is known for Claude Sonnet 4.5 only.

Which has the bigger context window, Claude Sonnet 4.5 or Mercury 2?

Claude Sonnet 4.5, with 1M tokens against 128K.

How many benchmarks is the Claude Sonnet 4.5 vs Mercury 2 comparison based on?

34 benchmarks have a result for both models as of October 21, 2026. Claude Sonnet 4.5's coding index rests on 2 independent benchmarks and Mercury 2's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next