Enter opens the highlighted result. Esc closes.

DeepSeek V3.1 Terminus vs Qwen2.5 72B Instruct

DeepSeek V3.1 Terminus leads Qwen2.5 72B Instruct on the Artificial Analysis Intelligence Index, 14.8 to 7.7, and Qwen2.5 72B Instruct costs 2.5x less per output token ($0.40 vs $1.0142 per million). Updated October 22, 2026; 31 benchmarks have a result for both.

Replace DeepSeek V3.1 Terminus Replace Qwen2.5 72B Instruct
DeepSeek V3.1 TerminusDeepSeek
Coding
No data
Overall
No data
Output $/M
$1.0142
31
Qwen2.5 72B InstructQwen
Coding
No data
Overall
26.5
Output $/M
$0.40
0
vs boards won of 31 shared

DeepSeek V3.1 Terminus or Qwen2.5 72B Instruct: 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 33K tokens).

Model ADeepSeek V3.1 TerminusDeepSeekNot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen2.5 72B InstructQwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
31
DeepSeek V3.1 Terminus only
14
Qwen2.5 72B Instruct only
22
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, Qwen2.5 72B Instruct not benchmarked.
Widest category
Math, 57.1 points apart on average over 3 shared benchmarks.
Widest single gap
AA Math Index: DeepSeek V3.1 Terminus 89.7 against Qwen2.5 72B Instruct 14.0, 75.7 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.1 Terminus $1.0142 against Qwen2.5 72B Instruct $0.40 per million output tokens, 2.5x apart.
Context window
DeepSeek V3.1 Terminus takes 164K tokens, Qwen2.5 72B Instruct 33K.

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 TerminusBarsQwen2.5 72B InstructTies
Coding40
Intelligence10
Agentic work10
Reasoning40
Math30
Knowledge50
General130
All shared boards310
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
Coding benchmarks for DeepSeek V3.1 Terminus and Qwen2.5 72B Instruct
BenchmarkDeepSeek V3.1 TerminusQwen2.5 72B InstructLeader
AA Coding Index43.5Not measuredOnly DeepSeek V3.1 Terminus measured
LiveCodeBench (Artificial Analysis run)79.8%27.6%DeepSeek V3.1 Terminus
SciCode38.0%Not measuredOnly DeepSeek V3.1 Terminus measured
Terminal-Bench Hard (Artificial Analysis run)31.8%4.5%DeepSeek V3.1 Terminus
WeirdMLNot measured16.0%Only Qwen2.5 72B Instruct measured
ALE-Bench745.2Not measuredOnly DeepSeek V3.1 Terminus measured
LMArena Text: coding14251292DeepSeek V3.1 Terminus
LMArena Text: software and IT14261292DeepSeek V3.1 Terminus
Neither model has a result on the other 31 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for DeepSeek V3.1 Terminus and Qwen2.5 72B Instruct
BenchmarkDeepSeek V3.1 TerminusQwen2.5 72B InstructLeader
AA Intelligence Index14.87.7DeepSeek V3.1 Terminus
Epoch Capabilities IndexNot measured129.0Only Qwen2.5 72B Instruct measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for DeepSeek V3.1 Terminus and Qwen2.5 72B Instruct
BenchmarkDeepSeek V3.1 TerminusQwen2.5 72B InstructLeader
AA Agentic Index6.8Not measuredOnly DeepSeek V3.1 Terminus measured
τ²-Bench Telecom37.1%34.5%DeepSeek V3.1 Terminus
METR time horizonsNot measured35.8%Only Qwen2.5 72B Instruct measured
BALROGNot measured16.2%Only Qwen2.5 72B Instruct measured
TheAgentCompanyNot measured5.7%Only Qwen2.5 72B Instruct measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index40
Reasoning benchmarks for DeepSeek V3.1 Terminus and Qwen2.5 72B Instruct
BenchmarkDeepSeek V3.1 TerminusQwen2.5 72B InstructLeader
GPQA Diamond (Artificial Analysis run)79.2%49.1%DeepSeek V3.1 Terminus
Humanity's Last Exam (Artificial Analysis run)16.4%3.6%DeepSeek V3.1 Terminus
GPQA Diamond (Epoch AI run)Not measured49.1%Only Qwen2.5 72B Instruct measured
BIG-Bench HardNot measured79.8%Only Qwen2.5 72B Instruct measured
LMArena Text: hard prompts14261271DeepSeek V3.1 Terminus
LMArena Text: expertNot measured1245Only Qwen2.5 72B Instruct measured
LMArena Text: hard prompts in English14321279DeepSeek V3.1 Terminus
Kagi LLM Benchmark57.4%Not measuredOnly DeepSeek V3.1 Terminus measured
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for DeepSeek V3.1 Terminus and Qwen2.5 72B Instruct
BenchmarkDeepSeek V3.1 TerminusQwen2.5 72B InstructLeader
AA Math Index89.714.0DeepSeek V3.1 Terminus
AIME 2025 (Artificial Analysis run)89.7%14.0%DeepSeek V3.1 Terminus
OTIS Mock AIMENot measured8.1%Only Qwen2.5 72B Instruct measured
MATH level 5Not measured63.2%Only Qwen2.5 72B Instruct measured
LMArena Text: math14021283DeepSeek V3.1 Terminus
LMArena Text: mathematical workNot measured1290Only Qwen2.5 72B Instruct measured
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for DeepSeek V3.1 Terminus and Qwen2.5 72B Instruct
BenchmarkDeepSeek V3.1 TerminusQwen2.5 72B InstructLeader
MMLU Pro (Artificial Analysis run)85.1%72.0%DeepSeek V3.1 Terminus
MMLUNot measured85.3%Only Qwen2.5 72B Instruct measured
AI2 Reasoning ChallengeNot measured94.5%Only Qwen2.5 72B Instruct measured
LMArena Text: science14511275DeepSeek V3.1 Terminus
LMArena Text: medicine and healthcare14681258DeepSeek V3.1 Terminus
LMArena Text: legal and government14571288DeepSeek V3.1 Terminus
LMArena Text: business and finance14141253DeepSeek V3.1 Terminus
Neither model has a result on the other 11 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for DeepSeek V3.1 Terminus and Qwen2.5 72B Instruct
BenchmarkDeepSeek V3.1 TerminusQwen2.5 72B InstructLeader
Design Arena: websites1187Not measuredOnly DeepSeek V3.1 Terminus measured
Design Arena: UI components1182Not measuredOnly DeepSeek V3.1 Terminus measured
Design Arena: game dev1131Not measuredOnly DeepSeek V3.1 Terminus measured
Design Arena: data viz1168Not measuredOnly DeepSeek V3.1 Terminus measured
Design Arena: 3D1141Not measuredOnly DeepSeek V3.1 Terminus measured
Design Arena: all code categories1175Not measuredOnly DeepSeek V3.1 Terminus measured
Design Arena: SVG1065Not measuredOnly DeepSeek V3.1 Terminus measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index130
General benchmarks for DeepSeek V3.1 Terminus and Qwen2.5 72B Instruct
BenchmarkDeepSeek V3.1 TerminusQwen2.5 72B InstructLeader
IFBench57.0%36.9%DeepSeek V3.1 Terminus
Long context reasoning (AA-LCR)69.3%Not measuredOnly DeepSeek V3.1 Terminus measured
DTBench81.3%62.9%DeepSeek V3.1 Terminus
LMCA28.6%13.4%DeepSeek V3.1 Terminus
HellaSwagNot measured84.8%Only Qwen2.5 72B Instruct measured
WinoGrandeNot measured82.3%Only Qwen2.5 72B Instruct measured
PIQANot measured82.6%Only Qwen2.5 72B Instruct measured
LMArena Text14191269DeepSeek V3.1 Terminus
LMArena Text: instruction following14041254DeepSeek V3.1 Terminus
LMArena Text: creative writing14031221DeepSeek V3.1 Terminus
LMArena Text: English14291283DeepSeek V3.1 Terminus
LMArena Text: non-English14081252DeepSeek V3.1 Terminus
LMArena Text: ChineseNot measured1273Only Qwen2.5 72B Instruct measured
LMArena Text: GermanNot measured1234Only Qwen2.5 72B Instruct measured
LMArena Text: JapaneseNot measured1180Only Qwen2.5 72B Instruct measured
LMArena Text: KoreanNot measured1188Only Qwen2.5 72B Instruct measured
LMArena Text: FrenchNot measured1280Only Qwen2.5 72B Instruct measured
LMArena Text: SpanishNot measured1255Only Qwen2.5 72B Instruct measured
LMArena Text: Russian14351264DeepSeek V3.1 Terminus
LMArena Text: Polish1427Not measuredOnly DeepSeek V3.1 Terminus measured
LMArena Text: multi-turn14111272DeepSeek V3.1 Terminus
LMArena Text: longer queries14221281DeepSeek V3.1 Terminus
LMArena Text: writing and language14091247DeepSeek V3.1 Terminus
LMArena Text: entertainment and media13911211DeepSeek V3.1 Terminus
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 DeepSeek V3.1 Terminus and Qwen2.5 72B Instruct
BenchmarkDeepSeek V3.1 TerminusQwen2.5 72B InstructLeader
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
Qwen2.5 72B Instruct$0.0006Fits in one request

Qwen2.5 72B Instruct costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.1 Terminus$0.018Fits in one request
Qwen2.5 72B Instruct$0.019Exceeds the context window

DeepSeek V3.1 Terminus costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.1 Terminus$0.071Exceeds the context window
Qwen2.5 72B Instruct$0.076Exceeds the context window

DeepSeek V3.1 Terminus 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 Qwen2.5 72B Instruct
SpecificationDeepSeek V3.1 TerminusQwen2.5 72B Instruct
MakerDeepSeekQwen
WeightsOpen weightsOpen weights
ReleasedSeptember 22, 2025September 19, 2024
Context window164K33K
Input $/Mtok$0.3063$0.36
Output $/Mtok$1.0142$0.40
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.1 Terminus better than Qwen2.5 72B Instruct 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 33K tokens).

Which is cheaper, DeepSeek V3.1 Terminus or Qwen2.5 72B Instruct?

DeepSeek V3.1 Terminus costs $0.3063 per million input tokens and $1.0142 per million output tokens; Qwen2.5 72B Instruct costs $0.36 and $0.40. Cost per solved task is known for neither of them.

Which has the bigger context window, DeepSeek V3.1 Terminus or Qwen2.5 72B Instruct?

DeepSeek V3.1 Terminus, with 164K tokens against 33K.

How many benchmarks is the DeepSeek V3.1 Terminus vs Qwen2.5 72B Instruct comparison based on?

31 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 Qwen2.5 72B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next