DeepSeek V3.2 vs Ling 3.0 Flash
DeepSeek V3.2 leads Ling 3.0 Flash on coding, 30.0 to 29.6 on the Vibe Coding Index, and Ling 3.0 Flash costs 7.2x less per output token ($0.1215 vs $0.88 per million). Updated October 22, 2026; 13 benchmarks have a result for both.
DeepSeek V3.2 or Ling 3.0 Flash: which to pick
DeepSeek V3.2 and Ling 3.0 Flash are level for coding, 30.0 against 29.6 on the Vibe Coding Index, so price and context decide.
Pick Ling 3.0 Flash for output tokens 7.2x cheaper ($0.1215 vs $0.88 per million) and a lower cost per solved task ($0.05 against $0.99). Pick DeepSeek V3.2 for work measured by SWE-bench Verified (Vals AI) or Vibe Code Bench (Vals AI), where it leads.
- Shared results
- 13
- DeepSeek V3.2 only
- 62
- Ling 3.0 Flash only
- 11
- Like-for-like categories
- 5 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.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Level: 30.0 against 29.6, inside 2 points.
3 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
DeepSeek V3.2
DeepSeek V3.2 leads, 21.5 against 20.1.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Ling 3.0 Flash has a AA Agentic Index result, 19.3.
Directional only
Reasoning
GPQA Diamond
Ling 3.0 Flash
Ling 3.0 Flash leads, 84.8% against 80.3%.
Same board, both measured
Math
AIME
No call
Only DeepSeek V3.2 has a AIME result, 84.6%.
Directional only
Knowledge
MMLU Pro
DeepSeek V3.2
DeepSeek V3.2 leads, 84.9% against 82.0%.
Same board, both measured
Web design
Design Arena: websites
No call
Only DeepSeek V3.2 has a Design Arena: websites result, 1175.
Directional only
Long documents
Listed context window
Ling 3.0 Flash
Ling 3.0 Flash takes 262K tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Ling 3.0 Flash
DeepSeek V3.2 $0.0007, Ling 3.0 Flash $0.0001 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Ling 3.0 Flash
DeepSeek V3.2 $0.99, Ling 3.0 Flash $0.05.
Published attempt cost and pass rate
At a glance
- Coding index
- DeepSeek V3.2 30.0 from 3 benchmarks, Ling 3.0 Flash 29.6 from 2 benchmarks.
- Widest category
- Knowledge, 5.0 points apart on average over 4 shared benchmarks.
- Widest single gap
- CorpFin (Vals AI): DeepSeek V3.2 51.0% against Ling 3.0 Flash 61.9%, 11.0 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3.2 $0.88 against Ling 3.0 Flash $0.1215 per million output tokens, 7.2x apart.
- Context window
- DeepSeek V3.2 takes 164K tokens, Ling 3.0 Flash 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.
| Category | DeepSeek V3.2 | Bars | Ling 3.0 Flash | Ties |
|---|---|---|---|---|
| Coding | 2 | 2 | ||
| Intelligence | 1 | 0 | ||
| Reasoning | 1 | 2 | ||
| Knowledge | 1 | 3 | ||
| General | 1 | 0 | ||
| All shared boards | 6 | 7 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index22
| Benchmark | DeepSeek V3.2 | Ling 3.0 Flash | Leader |
|---|---|---|---|
| SWE-bench Verified | 70.0% | Not measured | Only DeepSeek V3.2 measured |
| SWE-bench Multilingual | 59.0% | Not measured | Only DeepSeek V3.2 measured |
| LMArena WebDev | 1362 | Not measured | Only DeepSeek V3.2 measured |
| AA Coding Index | 44.2 | 50.6 | Ling 3.0 Flash |
| LiveCodeBench (Vals AI) | 80.7% | 84.0% | Ling 3.0 Flash |
| SWE-bench Verified (Vals AI) | 67.6% | 65.2% | DeepSeek V3.2 |
| Vibe Code Bench (Vals AI) | 5.1% | 2.9% | DeepSeek V3.2 |
| Code migration (Vals AI) | Not measured | 0.0% | Only Ling 3.0 Flash measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 50.2% | Only Ling 3.0 Flash measured |
| SkillsBench (Vals AI) | Not measured | 27.9% | Only Ling 3.0 Flash measured |
| LiveCodeBench (Artificial Analysis run) | 86.2% | Not measured | Only DeepSeek V3.2 measured |
| SciCode | Not measured | 42.0% | Only Ling 3.0 Flash measured |
| Terminal-Bench Hard (Artificial Analysis run) | 35.6% | Not measured | Only DeepSeek V3.2 measured |
| Terminal-Bench | 39.6% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: coding | 1453 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: software and IT | 1449 | Not measured | Only DeepSeek V3.2 measured |
| LMArena WebDev: React | 1350 | Not measured | Only DeepSeek V3.2 measured |
| LMArena WebDev: HTML | 1371 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 21 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V3.2 | Ling 3.0 Flash | Leader |
|---|---|---|---|
| AA Intelligence Index | 21.5 | 20.1 | DeepSeek V3.2 |
| Epoch Capabilities Index | 146.1 | Not measured | Only DeepSeek V3.2 measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | DeepSeek V3.2 | Ling 3.0 Flash | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 19.3 | Only Ling 3.0 Flash measured |
| Finance Agent (Vals AI) | Not measured | 30.3% | Only Ling 3.0 Flash measured |
| Legal Research Bench (Vals AI) | Not measured | 0.0% | Only Ling 3.0 Flash measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 25.0% | Only Ling 3.0 Flash measured |
| τ²-Bench Telecom | 90.6% | Not measured | Only DeepSeek V3.2 measured |
| APEX-Agents | 21.3% | Not measured | Only DeepSeek V3.2 measured |
| Vending-Bench 2 | $1,034 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 34 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | DeepSeek V3.2 | Ling 3.0 Flash | Leader |
|---|---|---|---|
| GPQA Diamond | 80.3% | 84.8% | Ling 3.0 Flash |
| GPQA Diamond (Artificial Analysis run) | 84.0% | 85.5% | Ling 3.0 Flash |
| Humanity's Last Exam (Artificial Analysis run) | 24.6% | 23.7% | DeepSeek V3.2 |
| ARC-AGI | 57.0% | Not measured | Only DeepSeek V3.2 measured |
| ARC-AGI-2 | 4.0% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: hard prompts | 1434 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: expert | 1436 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: hard prompts in English | 1446 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 14 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | DeepSeek V3.2 | Ling 3.0 Flash | Leader |
|---|---|---|---|
| AIME | 84.6% | Not measured | Only DeepSeek V3.2 measured |
| MGSM (Vals AI) | 86.0% | Not measured | Only DeepSeek V3.2 measured |
| AA Math Index | 92.0 | Not measured | Only DeepSeek V3.2 measured |
| AIME 2025 (Artificial Analysis run) | 92.0% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: math | 1435 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: mathematical work | 1440 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | DeepSeek V3.2 | Ling 3.0 Flash | Leader |
|---|---|---|---|
| MMLU Pro | 84.9% | 82.0% | DeepSeek V3.2 |
| LegalBench (Vals AI) | 76.1% | 79.7% | Ling 3.0 Flash |
| CaseLaw (Vals AI) | 55.4% | Not measured | Only DeepSeek V3.2 measured |
| CorpFin (Vals AI) | 51.0% | 61.9% | Ling 3.0 Flash |
| TaxEval (Vals AI) | 68.2% | 70.7% | Ling 3.0 Flash |
| MedQA (Vals AI) | 93.9% | Not measured | Only DeepSeek V3.2 measured |
| MedCode (Vals AI) | Not measured | 32.3% | Only Ling 3.0 Flash measured |
| MMLU Pro (Artificial Analysis run) | 86.2% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: science | 1446 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: medicine and healthcare | 1440 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: legal and government | 1425 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: business and finance | 1410 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 6 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | DeepSeek V3.2 | Ling 3.0 Flash | Leader |
|---|---|---|---|
| Design Arena: websites | 1175 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: UI components | 1146 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: game dev | 1131 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: data viz | 1158 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: 3D | 1132 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: all code categories | 1163 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: SVG | 1032 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: ASCII art | 1083 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V3.2 | Ling 3.0 Flash | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | Not measured | 50.7% | Only Ling 3.0 Flash measured |
| MedScribe (Vals AI) | Not measured | 80.9% | Only Ling 3.0 Flash measured |
| IFBench | 60.7% | Not measured | Only DeepSeek V3.2 measured |
| Long context reasoning (AA-LCR) | 73.3% | 73.0% | DeepSeek V3.2 |
| DTBench | 85.6% | Not measured | Only DeepSeek V3.2 measured |
| LMCA | 28.8% | Not measured | Only DeepSeek V3.2 measured |
| CL-bench | 12.4% | Not measured | Only DeepSeek V3.2 measured |
| CL-bench Life | 7.4% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text | 1425 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: instruction following | 1413 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: creative writing | 1400 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: English | 1439 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: non-English | 1409 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Chinese | 1455 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: German | 1413 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Japanese | 1374 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Korean | 1370 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: French | 1429 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Spanish | 1424 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Russian | 1424 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Polish | 1419 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: multi-turn | 1427 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: longer queries | 1428 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: writing and language | 1407 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: entertainment and media | 1395 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 21 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3.2 | Ling 3.0 Flash | Leader |
|---|---|---|---|
| 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
Ling 3.0 Flash costs less
Repository review
50K input + 3K output tokens
Ling 3.0 Flash costs less
Agent loop
200K input + 10K output tokens
Ling 3.0 Flash 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.
| Specification | DeepSeek V3.2 | inclusionAI Ling 3.0 Flash |
|---|---|---|
| Maker | DeepSeek | inclusionAI |
| Weights | Open weights | Open weights |
| Released | December 1, 2025 | July 23, 2026 |
| Context window | 164K | 262K |
| Input $/Mtok | $0.29 | $0.0405 |
| Output $/Mtok | $0.88 | $0.1215 |
| Coding index | 30.0 | 29.6 |
| Independent measurements behind it | 3 | 2 |
| Cost per solved task | $0.99 | $0.05 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3.2 better than Ling 3.0 Flash for coding?
DeepSeek V3.2 and Ling 3.0 Flash are level for coding, 30.0 against 29.6 on the Vibe Coding Index, so price and context decide. Pick Ling 3.0 Flash for output tokens 7.2x cheaper ($0.1215 vs $0.88 per million) and a lower cost per solved task ($0.05 against $0.99). Pick DeepSeek V3.2 for work measured by SWE-bench Verified (Vals AI) or Vibe Code Bench (Vals AI), where it leads.
Which is cheaper, DeepSeek V3.2 or Ling 3.0 Flash?
DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; Ling 3.0 Flash costs $0.0405 and $0.1215. Per solved SWE-bench Verified task, DeepSeek V3.2 costs $0.99 and Ling 3.0 Flash $0.05.
Which has the bigger context window, DeepSeek V3.2 or Ling 3.0 Flash?
Ling 3.0 Flash, with 262K tokens against 164K.
How many benchmarks is the DeepSeek V3.2 vs Ling 3.0 Flash comparison based on?
13 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.2's coding index rests on 3 independent benchmarks and Ling 3.0 Flash's on 2. Where only one model has a result, the page says so instead of naming a winner.