DeepSeek V3 0324 vs GLM 5.3 Flash
Updated October 21, 2026. 14 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick GLM 5.3 Flash for coding: it scores 71.0 on the Vibe Coding Index against 42.0 for DeepSeek V3 0324.
DeepSeek V3 0324 is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
- Shared results
- 14
- DeepSeek V3 0324 only
- 21
- GLM 5.3 Flash only
- 88
- Like-for-like categories
- 7 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.
Coding
Vibe Coding Index, four public coding benchmarks
GLM 5.3 Flash
GLM 5.3 Flash scores 71.0 against 42.0.
1 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
GLM 5.3 Flash
GLM 5.3 Flash leads, 41.8 against 9.7.
Same board, both measured
Agentic work
AA Agentic Index
GLM 5.3 Flash
GLM 5.3 Flash leads, 50.9 against 0.8.
Same board, both measured
Reasoning
GPQA Diamond
GLM 5.3 Flash
GLM 5.3 Flash leads, 86.4% against 61.6%.
Same board, both measured
Math
AIME
No call
Only DeepSeek V3 0324 has a AIME result, 52.2%.
Directional only
Knowledge
MMLU Pro
GLM 5.3 Flash
GLM 5.3 Flash leads, 86.1% against 79.5%.
Same board, both measured
Web design
Design Arena: websites
No call
Only GLM 5.3 Flash has a Design Arena: websites result, 1272.
Directional only
General
Vals Index
No call
Only GLM 5.3 Flash has a Vals Index result, 50.9%.
Directional only
Long documents
Listed context window
GLM 5.3 Flash
GLM 5.3 Flash takes 1.05M tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GLM 5.3 Flash
DeepSeek V3 0324 $0.0009, GLM 5.3 Flash $0.0004 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GLM 5.3 Flash has the number, $0.02.
Directional only
At a glance
- Coding index
- DeepSeek V3 0324 42.0 from 1 benchmark, GLM 5.3 Flash 71.0 from 2 benchmarks.
- Widest category
- Math, 56.1 points apart on average over 1 shared benchmark.
- Widest single gap
- OTIS Mock AIME: DeepSeek V3 0324 37.8% against GLM 5.3 Flash 93.9%, 56.1 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3 0324 $1.14 against GLM 5.3 Flash $0.50 per million output tokens, 2.3x apart.
- Context window
- DeepSeek V3 0324 takes 164K tokens, GLM 5.3 Flash 1.05M.
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 0324 | Bars | GLM 5.3 Flash | Ties |
|---|---|---|---|---|
| Coding | 0 | 3 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 4 | ||
| Math | 0 | 1 | ||
| Knowledge | 0 | 3 | ||
| General | 0 | 1 | ||
| All shared boards | 0 | 14 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index03
| Benchmark | DeepSeek V3 0324 | GLM 5.3 Flash | Leader |
|---|---|---|---|
| SWE-bench Verified | 42.0% | Not measured | Only DeepSeek V3 0324 measured |
| LiveBench coding | Not measured | 80.6% | Only GLM 5.3 Flash measured |
| LMArena WebDev | Not measured | 1607 | Only GLM 5.3 Flash measured |
| AA Coding Index | 21.2 | 71.5 | GLM 5.3 Flash |
| LiveCodeBench (Vals AI) | 65.5% | 80.5% | GLM 5.3 Flash |
| SWE-bench Verified (Vals AI) | Not measured | 92.0% | Only GLM 5.3 Flash measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 37.4% | Only GLM 5.3 Flash measured |
| Vibe Code Bench (Vals AI) | Not measured | 30.8% | Only GLM 5.3 Flash measured |
| Code migration (Vals AI) | Not measured | 20.5% | Only GLM 5.3 Flash measured |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only GLM 5.3 Flash measured |
| IOI (Vals AI) | Not measured | 52.5% | Only GLM 5.3 Flash measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 62.9% | Only GLM 5.3 Flash measured |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 16.0% | Only GLM 5.3 Flash measured |
| SkillsBench (Vals AI) | Not measured | 40.2% | Only GLM 5.3 Flash measured |
| CyberBench (Vals AI) | Not measured | 67.9% | Only GLM 5.3 Flash measured |
| LiveCodeBench (Artificial Analysis run) | 40.5% | Not measured | Only DeepSeek V3 0324 measured |
| SciCode | 39.0% | 51.6% | GLM 5.3 Flash |
| Terminal-Bench Hard (Artificial Analysis run) | 15.2% | Not measured | Only DeepSeek V3 0324 measured |
| FrontierCode | Not measured | 31.8% | Only GLM 5.3 Flash measured |
| FrontierSWE | Not measured | 18.1% | Only GLM 5.3 Flash measured |
| WeirdML | 36.1% | Not measured | Only DeepSeek V3 0324 measured |
| ALE-Bench | Not measured | 303.6 | Only GLM 5.3 Flash measured |
| LMArena Text: coding | Not measured | 1507 | Only GLM 5.3 Flash measured |
| LMArena Text: software and IT | Not measured | 1500 | Only GLM 5.3 Flash measured |
| LMArena WebDev: React | Not measured | 1624 | Only GLM 5.3 Flash measured |
| LMArena WebDev: HTML | Not measured | 1577 | Only GLM 5.3 Flash measured |
| LMArena WebDev: from an image | Not measured | 1578 | Only GLM 5.3 Flash measured |
| Neither model has a result on the other 11 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3 0324 | GLM 5.3 Flash | Leader |
|---|---|---|---|
| AA Intelligence Index | 9.7 | 41.8 | GLM 5.3 Flash |
| Epoch Capabilities Index | Not measured | 153.1 | Only GLM 5.3 Flash measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3 0324 | GLM 5.3 Flash | Leader |
|---|---|---|---|
| AA Agentic Index | 0.8 | 50.9 | GLM 5.3 Flash |
| LiveBench research | Not measured | 70.1% | Only GLM 5.3 Flash measured |
| LiveBench browser | Not measured | 84.0% | Only GLM 5.3 Flash measured |
| LiveBench long agentic | Not measured | 28.4% | Only GLM 5.3 Flash measured |
| SREBench (Vals AI) | Not measured | 0.8% | Only GLM 5.3 Flash measured |
| Finance Agent (Vals AI) | Not measured | 57.9% | Only GLM 5.3 Flash measured |
| Tax Agent Bench (Vals AI) | Not measured | 31.6% | Only GLM 5.3 Flash measured |
| Legal Research Bench (Vals AI) | Not measured | 45.2% | Only GLM 5.3 Flash measured |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 10.4% | Only GLM 5.3 Flash measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 55.9% | Only GLM 5.3 Flash measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 2.9% | Only GLM 5.3 Flash measured |
| τ²-Bench Telecom | 47.1% | Not measured | Only DeepSeek V3 0324 measured |
| APEX-Agents | Not measured | 52.8% | Only GLM 5.3 Flash measured |
| METR time horizons | 49.6% | Not measured | Only DeepSeek V3 0324 measured |
| Neither model has a result on the other 25 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | DeepSeek V3 0324 | GLM 5.3 Flash | Leader |
|---|---|---|---|
| GPQA Diamond | 61.6% | 86.4% | GLM 5.3 Flash |
| LiveBench reasoning | Not measured | 77.6% | Only GLM 5.3 Flash measured |
| MMMU Pro (Vals AI) | Not measured | 86.0% | Only GLM 5.3 Flash measured |
| GPQA Diamond (Artificial Analysis run) | 65.5% | 91.2% | GLM 5.3 Flash |
| Humanity's Last Exam (Artificial Analysis run) | 4.7% | 39.9% | GLM 5.3 Flash |
| GPQA Diamond (Epoch AI run) | 67.6% | 90.2% | GLM 5.3 Flash |
| ARC-AGI | Not measured | 91.0% | Only GLM 5.3 Flash measured |
| ARC-AGI-2 | Not measured | 65.8% | Only GLM 5.3 Flash measured |
| SimpleBench | 27.2% | Not measured | Only DeepSeek V3 0324 measured |
| Chess puzzles | Not measured | 21.0% | Only GLM 5.3 Flash measured |
| Mystery game puzzles | Not measured | 8.0% | Only GLM 5.3 Flash measured |
| LMArena Text: hard prompts | Not measured | 1490 | Only GLM 5.3 Flash measured |
| LMArena Text: expert | Not measured | 1511 | Only GLM 5.3 Flash measured |
| LMArena Text: hard prompts in English | Not measured | 1488 | Only GLM 5.3 Flash measured |
| LMArena Vision: diagrams | Not measured | 1317 | Only GLM 5.3 Flash measured |
| LMArena Vision: homework | Not measured | 1318 | Only GLM 5.3 Flash measured |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3 0324 | GLM 5.3 Flash | Leader |
|---|---|---|---|
| AIME | 52.2% | Not measured | Only DeepSeek V3 0324 measured |
| MATH 500 (Vals AI) | 88.6% | Not measured | Only DeepSeek V3 0324 measured |
| MGSM (Vals AI) | 91.7% | Not measured | Only DeepSeek V3 0324 measured |
| AA Math Index | 41.0 | Not measured | Only DeepSeek V3 0324 measured |
| AIME 2025 (Artificial Analysis run) | 41.0% | Not measured | Only DeepSeek V3 0324 measured |
| OTIS Mock AIME | 37.8% | 93.9% | GLM 5.3 Flash |
| FrontierMath, tiers 1 to 3 | Not measured | 55.8% | Only GLM 5.3 Flash measured |
| FrontierMath, tier 4 | Not measured | 17.1% | Only GLM 5.3 Flash measured |
| ProofBench | Not measured | 21.0% | Only GLM 5.3 Flash measured |
| MATH level 5 | 75.5% | Not measured | Only DeepSeek V3 0324 measured |
| LMArena Text: math | Not measured | 1503 | Only GLM 5.3 Flash measured |
| LMArena Text: mathematical work | Not measured | 1497 | Only GLM 5.3 Flash measured |
| Neither model has a result on the other 1 board here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | DeepSeek V3 0324 | GLM 5.3 Flash | Leader |
|---|---|---|---|
| MMLU Pro | 79.5% | 86.1% | GLM 5.3 Flash |
| LegalBench (Vals AI) | 77.7% | 83.9% | GLM 5.3 Flash |
| CorpFin (Vals AI) | 54.7% | Not measured | Only DeepSeek V3 0324 measured |
| TaxEval (Vals AI) | 71.1% | 75.6% | GLM 5.3 Flash |
| MedQA (Vals AI) | 82.0% | Not measured | Only DeepSeek V3 0324 measured |
| MMLU Pro (Artificial Analysis run) | 81.9% | Not measured | Only DeepSeek V3 0324 measured |
| LMArena Text: science | Not measured | 1484 | Only GLM 5.3 Flash measured |
| LMArena Text: medicine and healthcare | Not measured | 1475 | Only GLM 5.3 Flash measured |
| LMArena Text: legal and government | Not measured | 1473 | Only GLM 5.3 Flash measured |
| LMArena Text: business and finance | Not measured | 1460 | Only GLM 5.3 Flash measured |
| Neither model has a result on the other 7 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | DeepSeek V3 0324 | GLM 5.3 Flash | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1272 | Only GLM 5.3 Flash measured |
| Design Arena: UI components | Not measured | 1316 | Only GLM 5.3 Flash measured |
| Design Arena: game dev | Not measured | 1279 | Only GLM 5.3 Flash measured |
| Design Arena: data viz | Not measured | 1262 | Only GLM 5.3 Flash measured |
| Design Arena: 3D | Not measured | 1316 | Only GLM 5.3 Flash measured |
| Design Arena: all code categories | Not measured | 1282 | Only GLM 5.3 Flash measured |
| Design Arena: SVG | Not measured | 1284 | Only GLM 5.3 Flash measured |
| Design Arena: ASCII art | Not measured | 1269 | Only GLM 5.3 Flash measured |
| LiveBench design | Not measured | 77.2% | Only GLM 5.3 Flash measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3 0324 | GLM 5.3 Flash | Leader |
|---|---|---|---|
| Vals Index | Not measured | 50.9% | Only GLM 5.3 Flash measured |
| LiveBench data analysis | Not measured | 76.4% | Only GLM 5.3 Flash measured |
| MedScribe (Vals AI) | Not measured | 88.9% | Only GLM 5.3 Flash measured |
| IFBench | 41.0% | Not measured | Only DeepSeek V3 0324 measured |
| Long context reasoning (AA-LCR) | 40.7% | 80.0% | GLM 5.3 Flash |
| DTBench | 64.8% | Not measured | Only DeepSeek V3 0324 measured |
| LMCA | 15.5% | Not measured | Only DeepSeek V3 0324 measured |
| Fiction.LiveBench | 50.0% | Not measured | Only DeepSeek V3 0324 measured |
| Creative writing (Lech Mazur) | 77.0% | Not measured | Only DeepSeek V3 0324 measured |
| Surface Evolver Bench | Not measured | 52.5% | Only GLM 5.3 Flash measured |
| LMArena Text | Not measured | 1471 | Only GLM 5.3 Flash measured |
| LMArena Text: instruction following | Not measured | 1478 | Only GLM 5.3 Flash measured |
| LMArena Text: creative writing | Not measured | 1441 | Only GLM 5.3 Flash measured |
| LMArena Vision | Not measured | 1294 | Only GLM 5.3 Flash measured |
| LMArena Text: English | Not measured | 1474 | Only GLM 5.3 Flash measured |
| LMArena Text: non-English | Not measured | 1462 | Only GLM 5.3 Flash measured |
| LMArena Text: Chinese | Not measured | 1531 | Only GLM 5.3 Flash measured |
| LMArena Text: German | Not measured | 1462 | Only GLM 5.3 Flash measured |
| LMArena Text: Japanese | Not measured | 1444 | Only GLM 5.3 Flash measured |
| LMArena Text: Korean | Not measured | 1436 | Only GLM 5.3 Flash measured |
| LMArena Text: French | Not measured | 1491 | Only GLM 5.3 Flash measured |
| LMArena Text: Spanish | Not measured | 1475 | Only GLM 5.3 Flash measured |
| LMArena Text: Russian | Not measured | 1465 | Only GLM 5.3 Flash measured |
| LMArena Text: Polish | Not measured | 1450 | Only GLM 5.3 Flash measured |
| LMArena Text: multi-turn | Not measured | 1469 | Only GLM 5.3 Flash measured |
| LMArena Text: longer queries | Not measured | 1481 | Only GLM 5.3 Flash measured |
| LMArena Text: writing and language | Not measured | 1455 | Only GLM 5.3 Flash measured |
| LMArena Text: entertainment and media | Not measured | 1440 | Only GLM 5.3 Flash measured |
| LMArena Vision: English | Not measured | 1295 | Only GLM 5.3 Flash measured |
| LMArena Vision: Chinese | Not measured | 1363 | Only GLM 5.3 Flash measured |
| LMArena Vision: reading text | Not measured | 1299 | Only GLM 5.3 Flash measured |
| LMArena Vision: humor | Not measured | 1279 | Only GLM 5.3 Flash measured |
| LMArena Vision: creative writing | Not measured | 1270 | Only GLM 5.3 Flash measured |
| Neither model has a result on the other 13 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3 0324 | GLM 5.3 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
GLM 5.3 Flash costs less
Repository review
50K input + 3K output tokens
GLM 5.3 Flash costs less
Agent loop
200K input + 10K output tokens
GLM 5.3 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 0324 | Z.ai GLM 5.3 Flash |
|---|---|---|
| Maker | DeepSeek | Z.ai |
| Weights | Open weights | Open weights |
| Released | March 24, 2025 | August 26, 2026 |
| Context window | 164K | 1.05M |
| Input $/Mtok | $0.29 | $0.15 |
| Output $/Mtok | $1.14 | $0.50 |
| Coding index | 42.0 | 71.0 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | Not computable | $0.02 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3 0324 better than GLM 5.3 Flash for coding?
Pick GLM 5.3 Flash for coding: it scores 71.0 on the Vibe Coding Index against 42.0 for DeepSeek V3 0324. DeepSeek V3 0324 is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
Which is cheaper, DeepSeek V3 0324 or GLM 5.3 Flash?
DeepSeek V3 0324 costs $0.29 per million input tokens and $1.14 per million output tokens; GLM 5.3 Flash costs $0.15 and $0.50. Cost per solved task is known for GLM 5.3 Flash only.
Which has the bigger context window, DeepSeek V3 0324 or GLM 5.3 Flash?
GLM 5.3 Flash, with 1.05M tokens against 164K.
How many benchmarks is the DeepSeek V3 0324 vs GLM 5.3 Flash comparison based on?
14 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3 0324's coding index rests on 1 independent benchmark and GLM 5.3 Flash's on 2. Where only one model has a result, the page says so instead of naming a winner.