DeepSeek V3.2 Exp vs GLM 5
GLM 5 leads DeepSeek V3.2 Exp on the Artificial Analysis Intelligence Index, 27.9 to 16.6, and DeepSeek V3.2 Exp costs 7.8x less per output token ($0.41 vs $3.20 per million). Updated October 22, 2026; 48 benchmarks have a result for both.
DeepSeek V3.2 Exp or GLM 5: which to pick
Only GLM 5 has a coding score, 41.7 on the Vibe Coding Index; DeepSeek V3.2 Exp has none, so the two cannot be ranked on coding.
Pick DeepSeek V3.2 Exp for output tokens 7.8x cheaper ($0.41 vs $3.20 per million) and work measured by LMArena Text: medicine and healthcare or LMArena Text: Polish, where it leads.
- Shared results
- 48
- DeepSeek V3.2 Exp only
- 11
- GLM 5 only
- 28
- Like-for-like categories
- 8 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
Only GLM 5 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
GLM 5
GLM 5 leads, 27.9 against 16.6.
Same board, both measured
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 1178.
Same board, both measured
Long documents
Listed context window
GLM 5
GLM 5 takes 205K tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3.2 Exp
DeepSeek V3.2 Exp $0.0005, 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 V3.2 Exp not benchmarked, GLM 5 41.7 from 3 benchmarks.
- Widest category
- Agentic work, 64.3 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: DeepSeek V3.2 Exp 33.9% against GLM 5 98.2%, 64.3 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3.2 Exp $0.41 against GLM 5 $3.20 per million output tokens, 7.8x apart.
- Context window
- DeepSeek V3.2 Exp takes 164K 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 V3.2 Exp | Bars | GLM 5 | Ties |
|---|---|---|---|---|
| Coding | 0 | 6 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 6 | ||
| Math | 0 | 2 | ||
| Knowledge | 1 | 3 | ||
| Web design | 0 | 7 | ||
| General | 1 | 19 | ||
| All shared boards | 2 | 46 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index06
| Benchmark | DeepSeek V3.2 Exp | GLM 5 | Leader |
|---|---|---|---|
| Aider polyglot | 74.2% | Not measured | Only DeepSeek V3.2 Exp measured |
| SWE-bench Verified | Not measured | 72.8% | Only GLM 5 measured |
| SWE-bench Multilingual | Not measured | 69.7% | Only GLM 5 measured |
| LMArena WebDev | 1272 | 1435 | GLM 5 |
| 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 |
| LiveCodeBench (Artificial Analysis run) | 78.9% | Not measured | Only DeepSeek V3.2 Exp measured |
| Terminal-Bench Hard (Artificial Analysis run) | 31.1% | 43.2% | GLM 5 |
| Terminal-Bench | Not measured | 52.4% | Only GLM 5 measured |
| WeirdML | 39.5% | 48.2% | GLM 5 |
| ALE-Bench | Not measured | 765.6 | Only GLM 5 measured |
| LMArena Text: coding | 1438 | 1461 | GLM 5 |
| LMArena Text: software and IT | 1438 | 1460 | GLM 5 |
| LMArena WebDev: React | Not measured | 1424 | Only GLM 5 measured |
| LMArena WebDev: HTML | 1281 | 1450 | GLM 5 |
| Neither model has a result on the other 23 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V3.2 Exp | GLM 5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 16.6 | 27.9 | GLM 5 |
| Epoch Capabilities Index | 144.9 | 145.8 | GLM 5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.2 Exp | GLM 5 | Leader |
|---|---|---|---|
| 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 | 1147 | Only GLM 5 measured |
| Design Arena: agents building Godot games | Not measured | 1144 | Only GLM 5 measured |
| Design Arena: HTML slides | Not measured | 1098 | Only GLM 5 measured |
| τ²-Bench Telecom | 33.9% | 98.2% | GLM 5 |
| TheAgentCompany | 42.9% | Not measured | Only DeepSeek V3.2 Exp measured |
| Vending-Bench 2 | Not measured | $4,432 | Only GLM 5 measured |
| Berkeley Function Calling Leaderboard (BFCL) | 56.7% | Not measured | Only DeepSeek V3.2 Exp measured |
| Neither model has a result on the other 32 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | DeepSeek V3.2 Exp | GLM 5 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 83.3% | Only GLM 5 measured |
| GPQA Diamond (Artificial Analysis run) | 79.7% | 82.0% | GLM 5 |
| Humanity's Last Exam (Artificial Analysis run) | 14.9% | 29.3% | GLM 5 |
| 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 | Not measured | 53.2% | Only GLM 5 measured |
| LMArena Text: hard prompts | 1429 | 1452 | GLM 5 |
| LMArena Text: expert | 1422 | 1454 | GLM 5 |
| LMArena Text: hard prompts in English | 1444 | 1460 | GLM 5 |
| Kagi LLM Benchmark | 52.2% | 75.0% | 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 V3.2 Exp | GLM 5 | Leader |
|---|---|---|---|
| AIME | Not measured | 91.7% | Only GLM 5 measured |
| AA Math Index | 87.7 | Not measured | Only DeepSeek V3.2 Exp measured |
| AIME 2025 (Artificial Analysis run) | 87.7% | Not measured | Only DeepSeek V3.2 Exp measured |
| OTIS Mock AIME | Not measured | 80.0% | Only GLM 5 measured |
| LMArena Text: math | 1422 | 1440 | GLM 5 |
| LMArena Text: mathematical work | 1433 | 1451 | GLM 5 |
| 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 Exp | 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 |
| MMLU Pro (Artificial Analysis run) | 85.0% | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: science | 1443 | 1460 | GLM 5 |
| LMArena Text: medicine and healthcare | 1468 | 1455 | DeepSeek V3.2 Exp |
| LMArena Text: legal and government | 1419 | 1453 | GLM 5 |
| LMArena Text: business and finance | 1412 | 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 index07
| Benchmark | DeepSeek V3.2 Exp | GLM 5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1178 | 1247 | GLM 5 |
| Design Arena: UI components | 1164 | 1227 | GLM 5 |
| Design Arena: game dev | 1144 | 1234 | GLM 5 |
| Design Arena: data viz | 1152 | 1228 | GLM 5 |
| Design Arena: 3D | 1148 | 1228 | GLM 5 |
| Design Arena: all code categories | 1170 | 1246 | GLM 5 |
| Design Arena: SVG | 1031 | 1168 | GLM 5 |
| Design Arena: ASCII art | Not measured | 1147 | Only GLM 5 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index119
| Benchmark | DeepSeek V3.2 Exp | GLM 5 | Leader |
|---|---|---|---|
| IFBench | 54.1% | 72.3% | GLM 5 |
| Long context reasoning (AA-LCR) | 72.3% | 75.7% | GLM 5 |
| DTBench | 87.7% | Not measured | Only DeepSeek V3.2 Exp measured |
| LMCA | 29.1% | Not measured | Only DeepSeek V3.2 Exp measured |
| Fiction.LiveBench | 83.3% | Not measured | Only DeepSeek V3.2 Exp measured |
| CL-bench | 13.2% | 18.7% | GLM 5 |
| CL-bench Life | 9.5% | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text | 1425 | 1446 | GLM 5 |
| LMArena Text: instruction following | 1401 | 1428 | GLM 5 |
| LMArena Text: creative writing | 1404 | 1438 | GLM 5 |
| LMArena Text: English | 1441 | 1458 | GLM 5 |
| LMArena Text: non-English | 1404 | 1430 | GLM 5 |
| LMArena Text: Chinese | 1461 | 1511 | GLM 5 |
| LMArena Text: German | 1440 | 1447 | GLM 5 |
| LMArena Text: Japanese | 1331 | 1416 | GLM 5 |
| LMArena Text: Korean | 1372 | 1423 | GLM 5 |
| LMArena Text: French | 1434 | 1456 | GLM 5 |
| LMArena Text: Spanish | 1441 | 1454 | GLM 5 |
| LMArena Text: Russian | 1412 | 1436 | GLM 5 |
| LMArena Text: Polish | 1435 | 1434 | DeepSeek V3.2 Exp |
| LMArena Text: multi-turn | 1422 | 1456 | GLM 5 |
| LMArena Text: longer queries | 1418 | 1446 | GLM 5 |
| LMArena Text: writing and language | 1407 | 1437 | GLM 5 |
| LMArena Text: entertainment and media | 1407 | 1426 | GLM 5 |
| 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
| Benchmark | DeepSeek V3.2 Exp | 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 V3.2 Exp costs less
Repository review
50K input + 3K output tokens
DeepSeek V3.2 Exp costs less
Agent loop
200K input + 10K output tokens
DeepSeek V3.2 Exp 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 Exp | Z.ai GLM 5 |
|---|---|---|
| Maker | DeepSeek | Z.ai |
| Weights | Open weights | Open weights |
| Released | September 29, 2025 | February 11, 2026 |
| Context window | 164K | 205K |
| Input $/Mtok | $0.27 | $1.00 |
| Output $/Mtok | $0.41 | $3.20 |
| Coding index | Not benchmarked | 41.7 |
| Independent measurements behind it | 1 | 3 |
| Cost per solved task | Not computable | $0.63 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3.2 Exp better than GLM 5 for coding?
Only GLM 5 has a coding score, 41.7 on the Vibe Coding Index; DeepSeek V3.2 Exp has none, so the two cannot be ranked on coding. Pick DeepSeek V3.2 Exp for output tokens 7.8x cheaper ($0.41 vs $3.20 per million) and work measured by LMArena Text: medicine and healthcare or LMArena Text: Polish, where it leads.
Which is cheaper, DeepSeek V3.2 Exp or GLM 5?
DeepSeek V3.2 Exp costs $0.27 per million input tokens and $0.41 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 V3.2 Exp or GLM 5?
GLM 5, with 205K tokens against 164K.
How many benchmarks is the DeepSeek V3.2 Exp vs GLM 5 comparison based on?
48 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.2 Exp's coding index rests on 1 independent benchmark and GLM 5's on 3. Where only one model has a result, the page says so instead of naming a winner.