DeepSeek V3.1 vs GLM 5.2
GLM 5.2 leads DeepSeek V3.1 on the Artificial Analysis Intelligence Index, 33.7 to 13.7, and DeepSeek V3.1 costs 2.9x less per output token ($1.50 vs $4.40 per million). Updated October 21, 2026; 10 benchmarks have a result for both.
DeepSeek V3.1 or GLM 5.2: which to pick
Only GLM 5.2 has a coding score, 61.1 on the Vibe Coding Index; DeepSeek V3.1 has none, so the two cannot be ranked on coding.
Pick DeepSeek V3.1 for output tokens 2.9x cheaper ($1.50 vs $4.40 per million).
- Shared results
- 10
- DeepSeek V3.1 only
- 0
- GLM 5.2 only
- 87
- Like-for-like categories
- 3 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 5.2 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
GLM 5.2
GLM 5.2 leads, 33.7 against 13.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only GLM 5.2 has a AA Agentic Index result, 38.4.
Directional only
Reasoning
GPQA Diamond
No call
Only GLM 5.2 has a GPQA Diamond result, 85.6%.
Directional only
Knowledge
MMLU Pro
No call
Only GLM 5.2 has a MMLU Pro result, 86.7%.
Directional only
Web design
Design Arena: websites
GLM 5.2
GLM 5.2 leads, 1285 against 1123.
Same board, both measured
Long documents
Listed context window
GLM 5.2
GLM 5.2 takes 1.05M tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3.1
DeepSeek V3.1 $0.0013, GLM 5.2 $0.0036 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GLM 5.2 has the number, $0.86.
Directional only
At a glance
- Coding index
- DeepSeek V3.1 not benchmarked, GLM 5.2 61.1 from 4 benchmarks.
- Widest category
- Web design, 24.7 points apart on average over 7 shared benchmarks.
- Widest single gap
- Design Arena: SVG: DeepSeek V3.1 967 against GLM 5.2 1214, 30.9 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3.1 $1.50 against GLM 5.2 $4.40 per million output tokens, 2.9x apart.
- Context window
- DeepSeek V3.1 takes 164K tokens, GLM 5.2 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 V3.1 | Bars | GLM 5.2 | Ties |
|---|---|---|---|---|
| Intelligence | 0 | 1 | ||
| Web design | 0 | 7 | ||
| General | 0 | 2 | ||
| All shared boards | 0 | 10 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index18 boards, none shared
| Benchmark | DeepSeek V3.1 | GLM 5.2 | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1604 | Only GLM 5.2 measured |
| AA Coding Index | Not measured | 68.8 | Only GLM 5.2 measured |
| LiveCodeBench (Vals AI) | Not measured | 69.5% | Only GLM 5.2 measured |
| SWE-bench Verified (Vals AI) | Not measured | 82.8% | Only GLM 5.2 measured |
| Vibe Code Bench (Vals AI) | Not measured | 64.0% | Only GLM 5.2 measured |
| Code migration (Vals AI) | Not measured | 37.9% | Only GLM 5.2 measured |
| ProgramBench (Vals AI) | Not measured | 0.5% | Only GLM 5.2 measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 67.8% | Only GLM 5.2 measured |
| SkillsBench (Vals AI) | Not measured | 45.1% | Only GLM 5.2 measured |
| SciCode | Not measured | 51.2% | Only GLM 5.2 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 50.8% | Only GLM 5.2 measured |
| FrontierCode | Not measured | 24.5% | Only GLM 5.2 measured |
| WeirdML | Not measured | 70.1% | Only GLM 5.2 measured |
| ALE-Bench | Not measured | 1047.0 | Only GLM 5.2 measured |
| LMArena Text: coding | Not measured | 1487 | Only GLM 5.2 measured |
| LMArena Text: software and IT | Not measured | 1486 | Only GLM 5.2 measured |
| LMArena WebDev: React | Not measured | 1617 | Only GLM 5.2 measured |
| LMArena WebDev: HTML | Not measured | 1565 | Only GLM 5.2 measured |
| Neither model has a result on the other 20 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.1 | GLM 5.2 | Leader |
|---|---|---|---|
| AA Intelligence Index | 13.7 | 33.7 | GLM 5.2 |
| Epoch Capabilities Index | Not measured | 151.9 | Only GLM 5.2 measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index17 boards, none shared
| Benchmark | DeepSeek V3.1 | GLM 5.2 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 38.4 | Only GLM 5.2 measured |
| Design Arena: agents building web apps | Not measured | 1222 | Only GLM 5.2 measured |
| Design Arena: agents building full-stack apps | Not measured | 1241 | Only GLM 5.2 measured |
| Design Arena: agents building mobile apps | Not measured | 1160 | Only GLM 5.2 measured |
| Design Arena: agents building Android apps | Not measured | 1178 | Only GLM 5.2 measured |
| Design Arena: agents building Godot games | Not measured | 1142 | Only GLM 5.2 measured |
| Design Arena: agents building games | Not measured | 1206 | Only GLM 5.2 measured |
| Design Arena: HTML slides | Not measured | 1175 | Only GLM 5.2 measured |
| Design Arena: PowerPoint slides | Not measured | 1195 | Only GLM 5.2 measured |
| SREBench (Vals AI) | Not measured | 0.0% | Only GLM 5.2 measured |
| Finance Agent (Vals AI) | Not measured | 49.7% | Only GLM 5.2 measured |
| Legal Research Bench (Vals AI) | Not measured | 31.3% | Only GLM 5.2 measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 61.5% | Only GLM 5.2 measured |
| τ²-Bench Telecom | Not measured | 99.1% | Only GLM 5.2 measured |
| APEX-Agents | Not measured | 45.2% | Only GLM 5.2 measured |
| PostTrainBench | Not measured | 31.7% | Only GLM 5.2 measured |
| Vending-Bench 2 | Not measured | $8,314 | Only GLM 5.2 measured |
| Neither model has a result on the other 22 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index13 boards, none shared
| Benchmark | DeepSeek V3.1 | GLM 5.2 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 85.6% | Only GLM 5.2 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 89.5% | Only GLM 5.2 measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 41.1% | Only GLM 5.2 measured |
| GPQA Diamond (Epoch AI run) | Not measured | 91.9% | Only GLM 5.2 measured |
| ARC-AGI | Not measured | 77.0% | Only GLM 5.2 measured |
| ARC-AGI-2 | Not measured | 22.8% | Only GLM 5.2 measured |
| SimpleBench | Not measured | 58.8% | Only GLM 5.2 measured |
| Chess puzzles | Not measured | 22.0% | Only GLM 5.2 measured |
| Mystery game puzzles | Not measured | 19.0% | Only GLM 5.2 measured |
| EBR-bench | Not measured | 9.5% | Only GLM 5.2 measured |
| LMArena Text: hard prompts | Not measured | 1481 | Only GLM 5.2 measured |
| LMArena Text: expert | Not measured | 1487 | Only GLM 5.2 measured |
| LMArena Text: hard prompts in English | Not measured | 1481 | Only GLM 5.2 measured |
| Neither model has a result on the other 8 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | DeepSeek V3.1 | GLM 5.2 | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 86.4% | Only GLM 5.2 measured |
| FrontierMath, tiers 1 to 3 | Not measured | 59.2% | Only GLM 5.2 measured |
| FrontierMath, tier 4 | Not measured | 29.3% | Only GLM 5.2 measured |
| ProofBench | Not measured | 35.0% | Only GLM 5.2 measured |
| LMArena Text: math | Not measured | 1483 | Only GLM 5.2 measured |
| LMArena Text: mathematical work | Not measured | 1489 | Only GLM 5.2 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index10 boards, none shared
| Benchmark | DeepSeek V3.1 | GLM 5.2 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 86.7% | Only GLM 5.2 measured |
| LegalBench (Vals AI) | Not measured | 84.1% | Only GLM 5.2 measured |
| CorpFin (Vals AI) | Not measured | 66.1% | Only GLM 5.2 measured |
| TaxEval (Vals AI) | Not measured | 73.3% | Only GLM 5.2 measured |
| MedCode (Vals AI) | Not measured | 40.8% | Only GLM 5.2 measured |
| SimpleQA Verified | Not measured | 34.2% | Only GLM 5.2 measured |
| LMArena Text: science | Not measured | 1489 | Only GLM 5.2 measured |
| LMArena Text: medicine and healthcare | Not measured | 1475 | Only GLM 5.2 measured |
| LMArena Text: legal and government | Not measured | 1486 | Only GLM 5.2 measured |
| LMArena Text: business and finance | Not measured | 1451 | Only GLM 5.2 measured |
| 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 V3.1 | GLM 5.2 | Leader |
|---|---|---|---|
| Design Arena: websites | 1123 | 1285 | GLM 5.2 |
| Design Arena: UI components | 1085 | 1296 | GLM 5.2 |
| Design Arena: game dev | 1084 | 1268 | GLM 5.2 |
| Design Arena: data viz | 1095 | 1285 | GLM 5.2 |
| Design Arena: 3D | 1077 | 1288 | GLM 5.2 |
| Design Arena: all code categories | 1112 | 1288 | GLM 5.2 |
| Design Arena: SVG | 967 | 1214 | GLM 5.2 |
| Design Arena: ASCII art | Not measured | 1190 | Only GLM 5.2 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V3.1 | GLM 5.2 | Leader |
|---|---|---|---|
| MedScribe (Vals AI) | Not measured | 83.5% | Only GLM 5.2 measured |
| IFBench | Not measured | 73.3% | Only GLM 5.2 measured |
| Long context reasoning (AA-LCR) | Not measured | 78.3% | Only GLM 5.2 measured |
| DTBench | 82.7% | 93.6% | GLM 5.2 |
| LMCA | 24.3% | 45.8% | GLM 5.2 |
| Surface Evolver Bench | Not measured | 55.6% | Only GLM 5.2 measured |
| LMArena Text | Not measured | 1470 | Only GLM 5.2 measured |
| LMArena Text: instruction following | Not measured | 1466 | Only GLM 5.2 measured |
| LMArena Text: creative writing | Not measured | 1463 | Only GLM 5.2 measured |
| LMArena Text: English | Not measured | 1475 | Only GLM 5.2 measured |
| LMArena Text: non-English | Not measured | 1459 | Only GLM 5.2 measured |
| LMArena Text: Chinese | Not measured | 1522 | Only GLM 5.2 measured |
| LMArena Text: German | Not measured | 1470 | Only GLM 5.2 measured |
| LMArena Text: Japanese | Not measured | 1450 | Only GLM 5.2 measured |
| LMArena Text: Korean | Not measured | 1440 | Only GLM 5.2 measured |
| LMArena Text: French | Not measured | 1479 | Only GLM 5.2 measured |
| LMArena Text: Spanish | Not measured | 1478 | Only GLM 5.2 measured |
| LMArena Text: Russian | Not measured | 1468 | Only GLM 5.2 measured |
| LMArena Text: Polish | Not measured | 1456 | Only GLM 5.2 measured |
| LMArena Text: multi-turn | Not measured | 1469 | Only GLM 5.2 measured |
| LMArena Text: longer queries | Not measured | 1480 | Only GLM 5.2 measured |
| LMArena Text: writing and language | Not measured | 1463 | Only GLM 5.2 measured |
| LMArena Text: entertainment and media | Not measured | 1450 | Only GLM 5.2 measured |
| Neither model has a result on the other 23 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3.1 | GLM 5.2 | 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 V3.1 costs less
Repository review
50K input + 3K output tokens
DeepSeek V3.1 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V3.1 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 V3.1 | Z.ai GLM 5.2 |
|---|---|---|
| Maker | DeepSeek | Z.ai |
| Weights | Open weights | Open weights |
| Released | August 21, 2025 | June 16, 2026 |
| Context window | 164K | 1.05M |
| Input $/Mtok | $0.55 | $1.40 |
| Output $/Mtok | $1.50 | $4.40 |
| Coding index | Not benchmarked | 61.1 |
| Independent measurements behind it | 0 | 4 |
| Cost per solved task | Not computable | $0.86 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3.1 better than GLM 5.2 for coding?
Only GLM 5.2 has a coding score, 61.1 on the Vibe Coding Index; DeepSeek V3.1 has none, so the two cannot be ranked on coding. Pick DeepSeek V3.1 for output tokens 2.9x cheaper ($1.50 vs $4.40 per million).
Which is cheaper, DeepSeek V3.1 or GLM 5.2?
DeepSeek V3.1 costs $0.55 per million input tokens and $1.50 per million output tokens; GLM 5.2 costs $1.40 and $4.40. Cost per solved task is known for GLM 5.2 only.
Which has the bigger context window, DeepSeek V3.1 or GLM 5.2?
GLM 5.2, with 1.05M tokens against 164K.
How many benchmarks is the DeepSeek V3.1 vs GLM 5.2 comparison based on?
10 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.1's coding index rests on 0 independent benchmarks and GLM 5.2's on 4. Where only one model has a result, the page says so instead of naming a winner.