DeepSeek V4 Flash 0423 vs GLM 5
Updated October 21, 2026. 44 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 for coding: it scores 59.7 on the Vibe Coding Index against 54.6 for DeepSeek V4 Flash 0423.
Pick DeepSeek V4 Flash 0423 when output tokens cost 17.6x less, or when the context window is larger, 1.05M against 205K tokens.
- Shared results
- 44
- DeepSeek V4 Flash 0423 only
- 4
- GLM 5 only
- 31
- 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
GLM 5 scores 59.7 against 54.6.
1 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
GLM 5
GLM 5 leads, 27.9 against 24.4.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only DeepSeek V4 Flash 0423 has a AA Agentic Index result, 26.3.
Directional only
Reasoning
GPQA Diamond
No call
Only GLM 5 has a GPQA Diamond result, 83.3%.
Directional only
Math
AIME
No call
Only GLM 5 has a AIME result, 91.7%.
Directional only
Knowledge
MMLU Pro
No call
Only GLM 5 has a MMLU Pro result, 86.0%.
Directional only
Web design
Design Arena: websites
GLM 5
GLM 5 leads, 1247 against 1208.
Same board, both measured
Long documents
Listed context window
DeepSeek V4 Flash 0423
DeepSeek V4 Flash 0423 takes 1.05M tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4 Flash 0423
DeepSeek V4 Flash 0423 $0.0002, GLM 5 $0.0026 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GLM 5 has the number, $0.63.
Directional only
At a glance
- Coding index
- DeepSeek V4 Flash 0423 54.6 from 1 benchmark, GLM 5 59.7 from 2 benchmarks.
- Widest category
- Coding, 10.4 points apart on average over 7 shared benchmarks.
- Widest single gap
- LMArena WebDev: React: DeepSeek V4 Flash 0423 1585 against GLM 5 1424, 26.8 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Flash 0423 $0.182 against GLM 5 $3.20 per million output tokens, 17.6x apart.
- Context window
- DeepSeek V4 Flash 0423 takes 1.05M tokens, GLM 5 205K.
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 V4 Flash 0423 | Bars | GLM 5 | Ties |
|---|---|---|---|---|
| Coding | 3 | 4 | ||
| Intelligence | 1 | 1 | ||
| Reasoning | 0 | 4 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 4 | ||
| Web design | 0 | 8 | ||
| General | 1 | 16 | ||
| All shared boards | 5 | 39 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index34
| Benchmark | DeepSeek V4 Flash 0423 | GLM 5 | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 72.8% | Only GLM 5 measured |
| SWE-bench Multilingual | Not measured | 69.7% | Only GLM 5 measured |
| LMArena WebDev | 1582 | 1435 | DeepSeek V4 Flash 0423 |
| AA Coding Index | 52.0 | Not measured | Only DeepSeek V4 Flash 0423 measured |
| LiveCodeBench (Vals AI) | Not measured | 81.9% | Only GLM 5 measured |
| SWE-bench Verified (Vals AI) | Not measured | 71.4% | Only GLM 5 measured |
| Vibe Code Bench (Vals AI) | Not measured | 23.4% | Only GLM 5 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 43.2% | Only GLM 5 measured |
| Terminal-Bench | Not measured | 52.4% | Only GLM 5 measured |
| WeirdML | 45.6% | 48.2% | GLM 5 |
| ALE-Bench | 678.2 | 765.6 | GLM 5 |
| LMArena Text: coding | 1457 | 1461 | GLM 5 |
| LMArena Text: software and IT | 1453 | 1460 | GLM 5 |
| LMArena WebDev: React | 1585 | 1424 | DeepSeek V4 Flash 0423 |
| LMArena WebDev: HTML | 1558 | 1450 | DeepSeek V4 Flash 0423 |
| Neither model has a result on the other 23 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | DeepSeek V4 Flash 0423 | GLM 5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 24.4 | 27.9 | GLM 5 |
| Epoch Capabilities Index | 146.1 | 145.8 | DeepSeek V4 Flash 0423 |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | DeepSeek V4 Flash 0423 | GLM 5 | Leader |
|---|---|---|---|
| AA Agentic Index | 26.3 | Not measured | Only DeepSeek V4 Flash 0423 measured |
| Design Arena: agents building full-stack apps | Not measured | 1123 | Only GLM 5 measured |
| Design Arena: agents building mobile apps | Not measured | 1136 | Only GLM 5 measured |
| Design Arena: agents building Android apps | Not measured | 1152 | Only GLM 5 measured |
| Design Arena: agents building Godot games | Not measured | 1144 | Only GLM 5 measured |
| Design Arena: HTML slides | Not measured | 1148 | Only GLM 5 measured |
| τ²-Bench Telecom | Not measured | 98.2% | Only GLM 5 measured |
| Vending-Bench 2 | Not measured | $4,432 | Only GLM 5 measured |
| Neither model has a result on the other 31 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | DeepSeek V4 Flash 0423 | GLM 5 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 83.3% | Only GLM 5 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 82.0% | Only GLM 5 measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 29.3% | Only GLM 5 measured |
| GPQA Diamond (Epoch AI run) | Not measured | 87.8% | Only GLM 5 measured |
| ARC-AGI | Not measured | 44.7% | Only GLM 5 measured |
| ARC-AGI-2 | Not measured | 4.9% | Only GLM 5 measured |
| SimpleBench | 46.3% | 53.2% | GLM 5 |
| LMArena Text: hard prompts | 1444 | 1452 | GLM 5 |
| LMArena Text: expert | 1441 | 1454 | GLM 5 |
| LMArena Text: hard prompts in English | 1449 | 1460 | GLM 5 |
| Neither model has a result on the other 11 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V4 Flash 0423 | GLM 5 | Leader |
|---|---|---|---|
| AIME | Not measured | 91.7% | Only GLM 5 measured |
| OTIS Mock AIME | Not measured | 80.0% | Only GLM 5 measured |
| LMArena Text: math | 1426 | 1440 | GLM 5 |
| LMArena Text: mathematical work | 1432 | 1451 | GLM 5 |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | DeepSeek V4 Flash 0423 | GLM 5 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 86.0% | Only GLM 5 measured |
| LegalBench (Vals AI) | Not measured | 84.1% | Only GLM 5 measured |
| CaseLaw (Vals AI) | Not measured | 52.5% | Only GLM 5 measured |
| CorpFin (Vals AI) | Not measured | 62.9% | Only GLM 5 measured |
| TaxEval (Vals AI) | Not measured | 70.0% | Only GLM 5 measured |
| MedQA (Vals AI) | Not measured | 94.3% | Only GLM 5 measured |
| LMArena Text: science | 1446 | 1460 | GLM 5 |
| LMArena Text: medicine and healthcare | 1448 | 1455 | GLM 5 |
| LMArena Text: legal and government | 1439 | 1453 | GLM 5 |
| LMArena Text: business and finance | 1425 | 1430 | GLM 5 |
| Neither model has a result on the other 7 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index08
| Benchmark | DeepSeek V4 Flash 0423 | GLM 5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1208 | 1247 | GLM 5 |
| Design Arena: UI components | 1164 | 1230 | GLM 5 |
| Design Arena: game dev | 1197 | 1234 | GLM 5 |
| Design Arena: data viz | 1127 | 1228 | GLM 5 |
| Design Arena: 3D | 1189 | 1229 | GLM 5 |
| Design Arena: all code categories | 1205 | 1246 | GLM 5 |
| Design Arena: SVG | 1155 | 1168 | GLM 5 |
| Design Arena: ASCII art | 1109 | 1146 | GLM 5 |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index116
| Benchmark | DeepSeek V4 Flash 0423 | GLM 5 | Leader |
|---|---|---|---|
| IFBench | Not measured | 72.3% | Only GLM 5 measured |
| Long context reasoning (AA-LCR) | Not measured | 75.7% | Only GLM 5 measured |
| DTBench | 86.4% | Not measured | Only DeepSeek V4 Flash 0423 measured |
| LMCA | 35.9% | Not measured | Only DeepSeek V4 Flash 0423 measured |
| CL-bench | Not measured | 18.7% | Only GLM 5 measured |
| LMArena Text | 1432 | 1446 | GLM 5 |
| LMArena Text: instruction following | 1421 | 1428 | GLM 5 |
| LMArena Text: creative writing | 1403 | 1438 | GLM 5 |
| LMArena Text: English | 1441 | 1458 | GLM 5 |
| LMArena Text: non-English | 1419 | 1430 | GLM 5 |
| LMArena Text: Chinese | 1463 | 1511 | GLM 5 |
| LMArena Text: German | 1419 | 1447 | GLM 5 |
| LMArena Text: Japanese | 1389 | 1416 | GLM 5 |
| LMArena Text: Korean | 1383 | 1423 | GLM 5 |
| LMArena Text: French | 1439 | 1456 | GLM 5 |
| LMArena Text: Spanish | 1436 | 1454 | GLM 5 |
| LMArena Text: Russian | 1427 | 1436 | GLM 5 |
| LMArena Text: Polish | 1436 | 1434 | DeepSeek V4 Flash 0423 |
| LMArena Text: multi-turn | 1449 | 1456 | GLM 5 |
| LMArena Text: longer queries | 1434 | 1446 | GLM 5 |
| LMArena Text: writing and language | 1410 | 1437 | GLM 5 |
| LMArena Text: entertainment and media | 1400 | 1426 | GLM 5 |
| Neither model has a result on the other 24 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4 Flash 0423 | GLM 5 | 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
DeepSeek V4 Flash 0423 costs less
Repository review
50K input + 3K output tokens
DeepSeek V4 Flash 0423 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V4 Flash 0423 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 V4 Flash 0423 | Z.ai GLM 5 |
|---|---|---|
| Maker | DeepSeek | Z.ai |
| Weights | Open weights | Open weights |
| Released | April 24, 2026 | February 11, 2026 |
| Context window | 1.05M | 205K |
| Input $/Mtok | $0.091 | $1.00 |
| Output $/Mtok | $0.182 | $3.20 |
| Coding index | 54.6 | 59.7 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | Not computable | $0.63 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Flash 0423 better than GLM 5 for coding?
Pick GLM 5 for coding: it scores 59.7 on the Vibe Coding Index against 54.6 for DeepSeek V4 Flash 0423. Pick DeepSeek V4 Flash 0423 when output tokens cost 17.6x less, or when the context window is larger, 1.05M against 205K tokens.
Which is cheaper, DeepSeek V4 Flash 0423 or GLM 5?
DeepSeek V4 Flash 0423 costs $0.091 per million input tokens and $0.182 per million output tokens; GLM 5 costs $1.00 and $3.20. Cost per solved task is known for GLM 5 only.
Which has the bigger context window, DeepSeek V4 Flash 0423 or GLM 5?
DeepSeek V4 Flash 0423, with 1.05M tokens against 205K.
How many benchmarks is the DeepSeek V4 Flash 0423 vs GLM 5 comparison based on?
44 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Flash 0423's coding index rests on 1 independent benchmark and GLM 5's on 2. Where only one model has a result, the page says so instead of naming a winner.