Enter opens the highlighted result. Esc closes.

Granite 4.2 8B vs Mercury 3

Granite 4.2 8B costs 1.7x less per output token than Mercury 3 ($0.20 vs $0.35 per million). Updated October 22, 2026; no benchmark has tested both models yet.

Replace Granite 4.2 8B Replace Mercury 3
Granite 4.2 8BIBM Granite
Coding
No data
Overall
No data
Output $/M
$0.20
Mercury 3Inception
Coding
No data
Overall
No data
Output $/M
$0.35
vs $0.20 vs $0.35 per 1M output tokens. Granite 4.2 8B is 1.7x cheaper.

Granite 4.2 8B or Mercury 3: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick Granite 4.2 8B for output tokens 1.7x cheaper ($0.20 vs $0.35 per million).

Model AGranite 4.2 8BIBM GraniteNot benchmarkedNo coding benchmarkNo cost per solved taskModel BMercury 3InceptionNot benchmarkedNo coding benchmarkNo cost per solved task

No benchmark has tested both yet. Granite 4.2 8B has results on AA Coding Index, SciCode and LMArena Text: coding; Mercury 3 on Design Arena: websites, Design Arena: UI components and Design Arena: game dev. Compare them on price and context instead.

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
Granite 4.2 8B not benchmarked, Mercury 3 not benchmarked.
Widest category
None yet: no category has been tested on both models.
Widest single gap
None yet: no benchmark has tested both models.
Output price
Granite 4.2 8B $0.20 against Mercury 3 $0.35 per million output tokens, 1.7x apart.
Context window
Granite 4.2 8B takes 131K tokens, Mercury 3 1M.

Benchmark by benchmark

Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.

CodingDirectional onlySix of these boards feed the Vibe Coding Index4 boards measured
Coding benchmarks for Granite 4.2 8B and Mercury 3
BenchmarkGranite 4.2 8BMercury 3Leader
AA Coding Index22.4Not measuredOnly Granite 4.2 8B measured
SciCode31.5%Not measuredOnly Granite 4.2 8B measured
LMArena Text: coding1378Not measuredOnly Granite 4.2 8B measured
LMArena Text: software and IT1367Not measuredOnly Granite 4.2 8B measured
Neither model has a result on the other 39 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
Intelligence benchmarks for Granite 4.2 8B and Mercury 3
BenchmarkGranite 4.2 8BMercury 3Leader
AA Intelligence Index11.1Not measuredOnly Granite 4.2 8B measured
Neither model has a result on the other 1 board here
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
Agentic work benchmarks for Granite 4.2 8B and Mercury 3
BenchmarkGranite 4.2 8BMercury 3Leader
AA Agentic Index1.3Not measuredOnly Granite 4.2 8B measured
Neither model has a result on the other 41 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index5 boards measured
Reasoning benchmarks for Granite 4.2 8B and Mercury 3
BenchmarkGranite 4.2 8BMercury 3Leader
GPQA Diamond (Artificial Analysis run)63.1%Not measuredOnly Granite 4.2 8B measured
Humanity's Last Exam (Artificial Analysis run)9.7%Not measuredOnly Granite 4.2 8B measured
LMArena Text: hard prompts1327Not measuredOnly Granite 4.2 8B measured
LMArena Text: expert1386Not measuredOnly Granite 4.2 8B measured
LMArena Text: hard prompts in English1345Not measuredOnly Granite 4.2 8B measured
Neither model has a result on the other 18 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index4 boards measured
Knowledge benchmarks for Granite 4.2 8B and Mercury 3
BenchmarkGranite 4.2 8BMercury 3Leader
LMArena Text: science1336Not measuredOnly Granite 4.2 8B measured
LMArena Text: medicine and healthcare1336Not measuredOnly Granite 4.2 8B measured
LMArena Text: legal and government1327Not measuredOnly Granite 4.2 8B measured
LMArena Text: business and finance1322Not measuredOnly Granite 4.2 8B measured
Neither model has a result on the other 16 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index5 boards measured
Web design benchmarks for Granite 4.2 8B and Mercury 3
BenchmarkGranite 4.2 8BMercury 3Leader
Design Arena: websitesNot measured1229Only Mercury 3 measured
Design Arena: UI componentsNot measured1247Only Mercury 3 measured
Design Arena: game devNot measured1225Only Mercury 3 measured
Design Arena: data vizNot measured1205Only Mercury 3 measured
Design Arena: all code categoriesNot measured1231Only Mercury 3 measured
Neither model has a result on the other 4 boards here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index12 boards measured
General benchmarks for Granite 4.2 8B and Mercury 3
BenchmarkGranite 4.2 8BMercury 3Leader
Long context reasoning (AA-LCR)45.0%Not measuredOnly Granite 4.2 8B measured
LMArena Text1319Not measuredOnly Granite 4.2 8B measured
LMArena Text: instruction following1300Not measuredOnly Granite 4.2 8B measured
LMArena Text: creative writing1236Not measuredOnly Granite 4.2 8B measured
LMArena Text: English1337Not measuredOnly Granite 4.2 8B measured
LMArena Text: non-English1301Not measuredOnly Granite 4.2 8B measured
LMArena Text: Chinese1367Not measuredOnly Granite 4.2 8B measured
LMArena Text: Russian1282Not measuredOnly Granite 4.2 8B measured
LMArena Text: multi-turn1301Not measuredOnly Granite 4.2 8B measured
LMArena Text: longer queries1325Not measuredOnly Granite 4.2 8B measured
LMArena Text: writing and language1269Not measuredOnly Granite 4.2 8B measured
LMArena Text: entertainment and media1271Not measuredOnly Granite 4.2 8B measured
Neither model has a result on the other 36 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

Granite 4.2 8B$0.0002Fits in one request
Mercury 3$0.0003Fits in one request

Granite 4.2 8B costs less

Repository review

50K input + 3K output tokens

Granite 4.2 8B$0.0046Fits in one request
Mercury 3$0.0060Fits in one request

Granite 4.2 8B costs less

Agent loop

200K input + 10K output tokens

Granite 4.2 8B$0.018Exceeds the context window
Mercury 3$0.024Fits in one request

Granite 4.2 8B 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 Granite 4.2 8B and Mercury 3
SpecificationIBM Granite 4.2 8BInception Mercury 3
MakerIBM GraniteInception
WeightsOpen weightsNo public weights listed
ReleasedAugust 31, 2026October 16, 2026
Context window131K1M
Input $/Mtok$0.08$0.10
Output $/Mtok$0.20$0.35
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Granite 4.2 8B better than Mercury 3 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Granite 4.2 8B for output tokens 1.7x cheaper ($0.20 vs $0.35 per million).

Which is cheaper, Granite 4.2 8B or Mercury 3?

Granite 4.2 8B costs $0.08 per million input tokens and $0.20 per million output tokens; Mercury 3 costs $0.10 and $0.35. Cost per solved task is known for neither of them.

Which has the bigger context window, Granite 4.2 8B or Mercury 3?

Mercury 3, with 1M tokens against 131K.

Has any benchmark tested both Granite 4.2 8B and Mercury 3?

No benchmark has tested both yet. Granite 4.2 8B has results on AA Coding Index, SciCode and LMArena Text: coding; Mercury 3 on Design Arena: websites, Design Arena: UI components and Design Arena: game dev. Compare them on price and context instead. Data as of October 22, 2026.

Compare next