Enter opens the highlighted result. Esc closes.

DeepSeek V3.1 Terminus vs Mercury 2

DeepSeek V3.1 Terminus leads Mercury 2 on the Artificial Analysis Intelligence Index, 14.8 to 10.8, and Mercury 2 costs 1.4x less per output token ($0.75 vs $1.0142 per million). Updated October 22, 2026; 35 benchmarks have a result for both.

Replace DeepSeek V3.1 Terminus Replace Mercury 2
DeepSeek V3.1 TerminusDeepSeek
Coding
No data
Overall
No data
Output $/M
$1.0142
31
Mercury 2Inception
Coding
No data
Overall
No data
Output $/M
$0.75
4
vs boards won of 35 shared

DeepSeek V3.1 Terminus or Mercury 2: which to pick

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

Pick DeepSeek V3.1 Terminus for a larger context window (164K against 128K tokens) and work measured by ALE-Bench or τ²-Bench Telecom, where it leads.

Model ADeepSeek V3.1 TerminusDeepSeekNot benchmarkedNo coding benchmarkNo cost per solved taskModel BMercury 2InceptionNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
35
DeepSeek V3.1 Terminus only
10
Mercury 2 only
7
Like-for-like categories
7 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

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
DeepSeek V3.1 Terminus not benchmarked, Mercury 2 not benchmarked.
Widest category
Agentic work, 19.4 points apart on average over 2 shared benchmarks.
Widest single gap
τ²-Bench Telecom: DeepSeek V3.1 Terminus 37.1% against Mercury 2 70.8%, 33.6 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.1 Terminus $1.0142 against Mercury 2 $0.75 per million output tokens, 1.4x apart.
Context window
DeepSeek V3.1 Terminus takes 164K 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
CategoryDeepSeek V3.1 TerminusBarsMercury 2Ties
Coding51
Intelligence10
Agentic work11
Reasoning31
Knowledge30
Web design70
General111
All shared boards314
CodingLike-for-likeSix of these boards feed the Vibe Coding Index51
Coding benchmarks for DeepSeek V3.1 Terminus and Mercury 2
BenchmarkDeepSeek V3.1 TerminusMercury 2Leader
LMArena WebDevNot measured1171Only Mercury 2 measured
AA Coding Index43.531.1DeepSeek V3.1 Terminus
LiveCodeBench (Artificial Analysis run)79.8%Not measuredOnly DeepSeek V3.1 Terminus measured
SciCode38.0%37.7%DeepSeek V3.1 Terminus
Terminal-Bench Hard (Artificial Analysis run)31.8%26.5%DeepSeek V3.1 Terminus
WeirdMLNot measured43.2%Only Mercury 2 measured
ALE-Bench745.2785.6Mercury 2
LMArena Text: coding14251390DeepSeek V3.1 Terminus
LMArena Text: software and IT14261385DeepSeek V3.1 Terminus
LMArena WebDev: ReactNot measured1160Only Mercury 2 measured
LMArena WebDev: HTMLNot measured1199Only Mercury 2 measured
Neither model has a result on the other 28 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for DeepSeek V3.1 Terminus and Mercury 2
BenchmarkDeepSeek V3.1 TerminusMercury 2Leader
AA Intelligence Index14.810.8DeepSeek V3.1 Terminus
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
Agentic work benchmarks for DeepSeek V3.1 Terminus and Mercury 2
BenchmarkDeepSeek V3.1 TerminusMercury 2Leader
AA Agentic Index6.81.6DeepSeek V3.1 Terminus
τ²-Bench Telecom37.1%70.8%Mercury 2
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index31
Reasoning benchmarks for DeepSeek V3.1 Terminus and Mercury 2
BenchmarkDeepSeek V3.1 TerminusMercury 2Leader
GPQA Diamond (Artificial Analysis run)79.2%77.0%DeepSeek V3.1 Terminus
Humanity's Last Exam (Artificial Analysis run)16.4%17.1%Mercury 2
LMArena Text: hard prompts14261362DeepSeek V3.1 Terminus
LMArena Text: expertNot measured1358Only Mercury 2 measured
LMArena Text: hard prompts in English14321374DeepSeek V3.1 Terminus
Kagi LLM Benchmark57.4%Not measuredOnly DeepSeek V3.1 Terminus measured
Neither model has a result on the other 16 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
Math benchmarks for DeepSeek V3.1 Terminus and Mercury 2
BenchmarkDeepSeek V3.1 TerminusMercury 2Leader
AA Math Index89.7Not measuredOnly DeepSeek V3.1 Terminus measured
AIME 2025 (Artificial Analysis run)89.7%Not measuredOnly DeepSeek V3.1 Terminus measured
LMArena Text: math1402Not measuredOnly DeepSeek V3.1 Terminus measured
Neither model has a result on the other 10 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index30
Knowledge benchmarks for DeepSeek V3.1 Terminus and Mercury 2
BenchmarkDeepSeek V3.1 TerminusMercury 2Leader
MMLU Pro (Artificial Analysis run)85.1%Not measuredOnly DeepSeek V3.1 Terminus measured
LMArena Text: science14511343DeepSeek V3.1 Terminus
LMArena Text: medicine and healthcare14681363DeepSeek V3.1 Terminus
LMArena Text: legal and government1457Not measuredOnly DeepSeek V3.1 Terminus measured
LMArena Text: business and finance14141349DeepSeek V3.1 Terminus
Neither model has a result on the other 13 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index70
Web design benchmarks for DeepSeek V3.1 Terminus and Mercury 2
BenchmarkDeepSeek V3.1 TerminusMercury 2Leader
Design Arena: websites11871036DeepSeek V3.1 Terminus
Design Arena: UI components1182996DeepSeek V3.1 Terminus
Design Arena: game dev1131984DeepSeek V3.1 Terminus
Design Arena: data viz11681009DeepSeek V3.1 Terminus
Design Arena: 3D1141982DeepSeek V3.1 Terminus
Design Arena: all code categories11751021DeepSeek V3.1 Terminus
Design Arena: SVG1065998DeepSeek V3.1 Terminus
Design Arena: ASCII artNot measured988Only 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 index111
General benchmarks for DeepSeek V3.1 Terminus and Mercury 2
BenchmarkDeepSeek V3.1 TerminusMercury 2Leader
IFBench57.0%69.8%Mercury 2
Long context reasoning (AA-LCR)69.3%43.7%DeepSeek V3.1 Terminus
DTBench81.3%Not measuredOnly DeepSeek V3.1 Terminus measured
LMCA28.6%Not measuredOnly DeepSeek V3.1 Terminus measured
LMArena Text14191354DeepSeek V3.1 Terminus
LMArena Text: instruction following14041328DeepSeek V3.1 Terminus
LMArena Text: creative writing14031286DeepSeek V3.1 Terminus
LMArena Text: English14291378DeepSeek V3.1 Terminus
LMArena Text: non-English14081330DeepSeek V3.1 Terminus
LMArena Text: ChineseNot measured1414Only Mercury 2 measured
LMArena Text: Russian14351304DeepSeek V3.1 Terminus
LMArena Text: Polish1427Not measuredOnly DeepSeek V3.1 Terminus measured
LMArena Text: multi-turn14111357DeepSeek V3.1 Terminus
LMArena Text: longer queries14221329DeepSeek V3.1 Terminus
LMArena Text: writing and language14091300DeepSeek V3.1 Terminus
LMArena Text: entertainment and media13911314DeepSeek V3.1 Terminus
Neither model has a result on the other 30 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V3.1 Terminus and Mercury 2
BenchmarkDeepSeek V3.1 TerminusMercury 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

DeepSeek V3.1 Terminus$0.0008Fits in one request
Mercury 2$0.0006Fits in one request

Mercury 2 costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.1 Terminus$0.018Fits in one request
Mercury 2$0.015Fits in one request

Mercury 2 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.1 Terminus$0.071Exceeds the context window
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 DeepSeek V3.1 Terminus and Mercury 2
SpecificationDeepSeek V3.1 TerminusInception Mercury 2
MakerDeepSeekInception
WeightsOpen weightsNo public weights listed
ReleasedSeptember 22, 2025March 4, 2026
Context window164K128K
Input $/Mtok$0.3063$0.25
Output $/Mtok$1.0142$0.75
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it01
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.1 Terminus better than Mercury 2 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V3.1 Terminus for a larger context window (164K against 128K tokens) and work measured by ALE-Bench or τ²-Bench Telecom, where it leads.

Which is cheaper, DeepSeek V3.1 Terminus or Mercury 2?

DeepSeek V3.1 Terminus costs $0.3063 per million input tokens and $1.0142 per million output tokens; Mercury 2 costs $0.25 and $0.75. Cost per solved task is known for neither of them.

Which has the bigger context window, DeepSeek V3.1 Terminus or Mercury 2?

DeepSeek V3.1 Terminus, with 164K tokens against 128K.

How many benchmarks is the DeepSeek V3.1 Terminus vs Mercury 2 comparison based on?

35 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.1 Terminus's coding index rests on 0 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