LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

DeepSeek V3 0324 vs Qwen3.5-122B-A10B

Updated October 21, 2026. 11 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace DeepSeek V3 0324 Replace Qwen3.5-122B-A10B
DeepSeek V3 0324DeepSeek
Coding
42.0
Overall
9.7
Output $/M
$1.14
0
Qwen3.5-122B-A10BQwen
Coding
22.9
Overall
17.7
Output $/M
$2.08
11
vs boards won of 11 shared

Decision reading

Pick DeepSeek V3 0324 for coding: it scores 42.0 on the Vibe Coding Index against 22.9 for Qwen3.5-122B-A10B.

Pick Qwen3.5-122B-A10B when the context window is larger, 262K against 164K tokens, or when what matters is AA Coding Index or SciCode, where it leads.

Model ADeepSeek V3 0324DeepSeek42.0/1001 independent benchmarkNo cost per solved taskModel BQwen3.5-122B-A10BQwen22.9/1001 independent benchmarkNo cost per solved task
Shared results
11
DeepSeek V3 0324 only
24
Qwen3.5-122B-A10B only
40
Like-for-like categories
5 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
DeepSeek V3 0324 42.0 from 1 benchmark, Qwen3.5-122B-A10B 22.9 from 1 benchmark.
Widest category
Agentic work, 46.5 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: DeepSeek V3 0324 47.1% against Qwen3.5-122B-A10B 93.6%, 46.5 points apart on a 0 to 100 scale.
Output price
DeepSeek V3 0324 $1.14 against Qwen3.5-122B-A10B $2.08 per million output tokens, 1.8x apart.
Context window
DeepSeek V3 0324 takes 164K tokens, Qwen3.5-122B-A10B 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
CategoryDeepSeek V3 0324BarsQwen3.5-122B-A10BTies
Coding03
Intelligence01
Agentic work01
Reasoning02
General04
All shared boards011
CodingLike-for-likeFour of these boards feed the Vibe Coding Index03
Coding benchmarks for DeepSeek V3 0324 and Qwen3.5-122B-A10B
BenchmarkDeepSeek V3 0324Qwen3.5-122B-A10BLeader
SWE-bench Verified42.0%Not measuredOnly DeepSeek V3 0324 measured
LMArena WebDevNot measured1361Only Qwen3.5-122B-A10B measured
AA Coding Index21.243.3Qwen3.5-122B-A10B
LiveCodeBench (Vals AI)65.5%Not measuredOnly DeepSeek V3 0324 measured
LiveCodeBench (Artificial Analysis run)40.5%Not measuredOnly DeepSeek V3 0324 measured
SciCode39.0%39.7%Qwen3.5-122B-A10B
Terminal-Bench Hard (Artificial Analysis run)15.2%31.1%Qwen3.5-122B-A10B
WeirdML36.1%Not measuredOnly DeepSeek V3 0324 measured
LMArena Text: codingNot measured1436Only Qwen3.5-122B-A10B measured
LMArena Text: software and ITNot measured1436Only Qwen3.5-122B-A10B measured
LMArena WebDev: ReactNot measured1353Only Qwen3.5-122B-A10B measured
LMArena WebDev: HTMLNot measured1351Only Qwen3.5-122B-A10B measured
Neither model has a result on the other 26 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for DeepSeek V3 0324 and Qwen3.5-122B-A10B
BenchmarkDeepSeek V3 0324Qwen3.5-122B-A10BLeader
AA Intelligence Index9.717.7Qwen3.5-122B-A10B
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for DeepSeek V3 0324 and Qwen3.5-122B-A10B
BenchmarkDeepSeek V3 0324Qwen3.5-122B-A10BLeader
AA Agentic Index0.8Not measuredOnly DeepSeek V3 0324 measured
τ²-Bench Telecom47.1%93.6%Qwen3.5-122B-A10B
METR time horizons49.6%Not measuredOnly DeepSeek V3 0324 measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
Reasoning benchmarks for DeepSeek V3 0324 and Qwen3.5-122B-A10B
BenchmarkDeepSeek V3 0324Qwen3.5-122B-A10BLeader
GPQA Diamond61.6%Not measuredOnly DeepSeek V3 0324 measured
GPQA Diamond (Artificial Analysis run)65.5%85.7%Qwen3.5-122B-A10B
Humanity's Last Exam (Artificial Analysis run)4.7%25.2%Qwen3.5-122B-A10B
GPQA Diamond (Epoch AI run)67.6%Not measuredOnly DeepSeek V3 0324 measured
SimpleBench27.2%Not measuredOnly DeepSeek V3 0324 measured
Mystery game puzzlesNot measured17.0%Only Qwen3.5-122B-A10B measured
LMArena Text: hard promptsNot measured1421Only Qwen3.5-122B-A10B measured
LMArena Text: expertNot measured1431Only Qwen3.5-122B-A10B measured
LMArena Text: hard prompts in EnglishNot measured1431Only Qwen3.5-122B-A10B measured
LMArena Vision: diagramsNot measured1249Only Qwen3.5-122B-A10B measured
LMArena Vision: homeworkNot measured1261Only Qwen3.5-122B-A10B measured
Neither model has a result on the other 10 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Math benchmarks for DeepSeek V3 0324 and Qwen3.5-122B-A10B
BenchmarkDeepSeek V3 0324Qwen3.5-122B-A10BLeader
AIME52.2%Not measuredOnly DeepSeek V3 0324 measured
MATH 500 (Vals AI)88.6%Not measuredOnly DeepSeek V3 0324 measured
MGSM (Vals AI)91.7%Not measuredOnly DeepSeek V3 0324 measured
AA Math Index41.0Not measuredOnly DeepSeek V3 0324 measured
AIME 2025 (Artificial Analysis run)41.0%Not measuredOnly DeepSeek V3 0324 measured
OTIS Mock AIME37.8%Not measuredOnly DeepSeek V3 0324 measured
MATH level 575.5%Not measuredOnly DeepSeek V3 0324 measured
LMArena Text: mathNot measured1431Only Qwen3.5-122B-A10B measured
LMArena Text: mathematical workNot measured1431Only Qwen3.5-122B-A10B measured
Neither model has a result on the other 4 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index10 boards, none shared
Knowledge benchmarks for DeepSeek V3 0324 and Qwen3.5-122B-A10B
BenchmarkDeepSeek V3 0324Qwen3.5-122B-A10BLeader
MMLU Pro79.5%Not measuredOnly DeepSeek V3 0324 measured
LegalBench (Vals AI)77.7%Not measuredOnly DeepSeek V3 0324 measured
CorpFin (Vals AI)54.7%Not measuredOnly DeepSeek V3 0324 measured
TaxEval (Vals AI)71.1%Not measuredOnly DeepSeek V3 0324 measured
MedQA (Vals AI)82.0%Not measuredOnly DeepSeek V3 0324 measured
MMLU Pro (Artificial Analysis run)81.9%Not measuredOnly DeepSeek V3 0324 measured
LMArena Text: scienceNot measured1432Only Qwen3.5-122B-A10B measured
LMArena Text: medicine and healthcareNot measured1423Only Qwen3.5-122B-A10B measured
LMArena Text: legal and governmentNot measured1422Only Qwen3.5-122B-A10B measured
LMArena Text: business and financeNot measured1414Only Qwen3.5-122B-A10B measured
Neither model has a result on the other 7 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for DeepSeek V3 0324 and Qwen3.5-122B-A10B
BenchmarkDeepSeek V3 0324Qwen3.5-122B-A10BLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index04
General benchmarks for DeepSeek V3 0324 and Qwen3.5-122B-A10B
BenchmarkDeepSeek V3 0324Qwen3.5-122B-A10BLeader
IFBench41.0%75.7%Qwen3.5-122B-A10B
Long context reasoning (AA-LCR)40.7%76.3%Qwen3.5-122B-A10B
DTBench64.8%84.3%Qwen3.5-122B-A10B
LMCA15.5%32.2%Qwen3.5-122B-A10B
Fiction.LiveBench50.0%Not measuredOnly DeepSeek V3 0324 measured
Creative writing (Lech Mazur)77.0%Not measuredOnly DeepSeek V3 0324 measured
LMArena TextNot measured1417Only Qwen3.5-122B-A10B measured
LMArena Text: instruction followingNot measured1399Only Qwen3.5-122B-A10B measured
LMArena Text: creative writingNot measured1368Only Qwen3.5-122B-A10B measured
LMArena VisionNot measured1244Only Qwen3.5-122B-A10B measured
LMArena Text: EnglishNot measured1428Only Qwen3.5-122B-A10B measured
LMArena Text: non-EnglishNot measured1401Only Qwen3.5-122B-A10B measured
LMArena Text: ChineseNot measured1463Only Qwen3.5-122B-A10B measured
LMArena Text: GermanNot measured1425Only Qwen3.5-122B-A10B measured
LMArena Text: JapaneseNot measured1367Only Qwen3.5-122B-A10B measured
LMArena Text: KoreanNot measured1353Only Qwen3.5-122B-A10B measured
LMArena Text: FrenchNot measured1443Only Qwen3.5-122B-A10B measured
LMArena Text: SpanishNot measured1425Only Qwen3.5-122B-A10B measured
LMArena Text: RussianNot measured1400Only Qwen3.5-122B-A10B measured
LMArena Text: PolishNot measured1398Only Qwen3.5-122B-A10B measured
LMArena Text: multi-turnNot measured1416Only Qwen3.5-122B-A10B measured
LMArena Text: longer queriesNot measured1410Only Qwen3.5-122B-A10B measured
LMArena Text: writing and languageNot measured1387Only Qwen3.5-122B-A10B measured
LMArena Text: entertainment and mediaNot measured1366Only Qwen3.5-122B-A10B measured
LMArena Vision: EnglishNot measured1249Only Qwen3.5-122B-A10B measured
LMArena Vision: ChineseNot measured1301Only Qwen3.5-122B-A10B measured
LMArena Vision: reading textNot measured1251Only Qwen3.5-122B-A10B measured
LMArena Vision: humorNot measured1243Only Qwen3.5-122B-A10B measured
LMArena Vision: creative writingNot measured1220Only Qwen3.5-122B-A10B measured
Neither model has a result on the other 17 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V3 0324 and Qwen3.5-122B-A10B
BenchmarkDeepSeek V3 0324Qwen3.5-122B-A10BLeader
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 0324$0.0009Fits in one request
Qwen3.5-122B-A10B$0.0013Fits in one request

DeepSeek V3 0324 costs less

Repository review

50K input + 3K output tokens

DeepSeek V3 0324$0.018Fits in one request
Qwen3.5-122B-A10B$0.019Fits in one request

DeepSeek V3 0324 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3 0324$0.069Exceeds the context window
Qwen3.5-122B-A10B$0.073Fits in one request

DeepSeek V3 0324 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 0324 and Qwen3.5-122B-A10B
SpecificationDeepSeek V3 0324Qwen3.5-122B-A10B
MakerDeepSeekQwen
WeightsOpen weightsOpen weights
ReleasedMarch 24, 2025February 25, 2026
Context window164K262K
Input $/Mtok$0.29$0.26
Output $/Mtok$1.14$2.08
Coding index42.022.9
Independent measurements behind it11
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3 0324 better than Qwen3.5-122B-A10B for coding?

Pick DeepSeek V3 0324 for coding: it scores 42.0 on the Vibe Coding Index against 22.9 for Qwen3.5-122B-A10B. Pick Qwen3.5-122B-A10B when the context window is larger, 262K against 164K tokens, or when what matters is AA Coding Index or SciCode, where it leads.

Which is cheaper, DeepSeek V3 0324 or Qwen3.5-122B-A10B?

DeepSeek V3 0324 costs $0.29 per million input tokens and $1.14 per million output tokens; Qwen3.5-122B-A10B costs $0.26 and $2.08. Cost per solved task is known for neither of them.

Which has the bigger context window, DeepSeek V3 0324 or Qwen3.5-122B-A10B?

Qwen3.5-122B-A10B, with 262K tokens against 164K.

How many benchmarks is the DeepSeek V3 0324 vs Qwen3.5-122B-A10B comparison based on?

11 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3 0324's coding index rests on 1 independent benchmark and Qwen3.5-122B-A10B's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next