GLM 5.2 vs Kimi K2.5
Updated October 21, 2026. 74 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
GLM 5.2 and Kimi K2.5 are level for coding, 57.7 against 58.5 on the Vibe Coding Index, so price and context decide.
Pick GLM 5.2 when the context window is larger, 1.05M against 262K tokens, or when what matters is LMArena WebDev or AA Coding Index, where it leads. Pick Kimi K2.5 when output tokens cost 2.8x less, or when a solved task costs $0.24 against $0.86.
- Shared results
- 74
- GLM 5.2 only
- 23
- Kimi K2.5 only
- 24
- Like-for-like categories
- 8 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
No call
Level: 57.7 against 58.5, inside 2 points.
1 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
GLM 5.2
GLM 5.2 leads, 33.7 against 23.5.
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
GLM 5.2
GLM 5.2 leads, 85.6% against 84.1%.
Same board, both measured
Math
AIME
No call
Only Kimi K2.5 has a AIME result, 95.6%.
Directional only
Knowledge
MMLU Pro
GLM 5.2
GLM 5.2 leads, 86.7% against 85.9%.
Same board, both measured
Web design
Design Arena: websites
GLM 5.2
GLM 5.2 leads, 1285 against 1249.
Same board, both measured
Long documents
Listed context window
GLM 5.2
GLM 5.2 takes 1.05M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Kimi K2.5
GLM 5.2 $0.0035, Kimi K2.5 $0.0018 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Kimi K2.5
GLM 5.2 $0.86, Kimi K2.5 $0.24.
Published attempt cost and pass rate
At a glance
- Coding index
- GLM 5.2 57.7 from 1 benchmark, Kimi K2.5 58.5 from 2 benchmarks.
- Widest category
- Coding, 19.9 points apart on average over 14 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): GLM 5.2 64.0% against Kimi K2.5 17.5%, 46.4 points apart on a 0 to 100 scale.
- Output price
- GLM 5.2 $7.00 against Kimi K2.5 $2.50 per million output tokens, 2.8x apart.
- Context window
- GLM 5.2 takes 1.05M tokens, Kimi K2.5 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 | GLM 5.2 | Bars | Kimi K2.5 | Ties |
|---|---|---|---|---|
| Coding | 13 | 1 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 9 | 1 | ||
| Reasoning | 9 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 6 | 3 | ||
| Web design | 8 | 0 | ||
| General | 20 | 0 | ||
| All shared boards | 69 | 5 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index131
| Benchmark | GLM 5.2 | Kimi K2.5 | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 70.8% | Only Kimi K2.5 measured |
| SWE-bench Multilingual | Not measured | 67.3% | Only Kimi K2.5 measured |
| LMArena WebDev | 1604 | 1437 | GLM 5.2 |
| AA Coding Index | 68.8 | 46.8 | GLM 5.2 |
| LiveCodeBench (Vals AI) | 69.5% | 83.9% | Kimi K2.5 |
| SWE-bench Verified (Vals AI) | 82.8% | 70.0% | GLM 5.2 |
| Vibe Code Bench (Vals AI) | 64.0% | 17.5% | GLM 5.2 |
| Code migration (Vals AI) | 37.9% | 7.0% | GLM 5.2 |
| ProgramBench (Vals AI) | 0.5% | Not measured | Only GLM 5.2 measured |
| Terminal-Bench 2.1 (Vals AI) | 67.8% | 42.0% | GLM 5.2 |
| SkillsBench (Vals AI) | 45.1% | Not measured | Only GLM 5.2 measured |
| SciCode | 51.2% | Not measured | Only GLM 5.2 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 50.8% | 34.8% | GLM 5.2 |
| Terminal-Bench | Not measured | 43.2% | Only Kimi K2.5 measured |
| FrontierCode | 24.5% | Not measured | Only GLM 5.2 measured |
| WeirdML | 70.1% | 45.6% | GLM 5.2 |
| ALE-Bench | 1047.0 | 821.6 | GLM 5.2 |
| LMArena Text: coding | 1487 | 1483 | GLM 5.2 |
| LMArena Text: software and IT | 1486 | 1471 | GLM 5.2 |
| LMArena WebDev: React | 1617 | 1429 | GLM 5.2 |
| LMArena WebDev: HTML | 1565 | 1426 | GLM 5.2 |
| LMArena WebDev: from an image | Not measured | 1439 | Only Kimi K2.5 measured |
| Neither model has a result on the other 16 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GLM 5.2 | Kimi K2.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 33.7 | 23.5 | GLM 5.2 |
| Epoch Capabilities Index | 151.9 | 148.1 | GLM 5.2 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index91
| Benchmark | GLM 5.2 | Kimi K2.5 | Leader |
|---|---|---|---|
| AA Agentic Index | 38.4 | Not measured | Only GLM 5.2 measured |
| Design Arena: agents building web apps | 1222 | 1136 | GLM 5.2 |
| Design Arena: agents building full-stack apps | 1241 | 1114 | GLM 5.2 |
| Design Arena: agents building mobile apps | 1160 | 1147 | GLM 5.2 |
| Design Arena: agents building Android apps | 1184 | 1124 | GLM 5.2 |
| Design Arena: agents building Godot games | 1142 | 1219 | Kimi K2.5 |
| Design Arena: agents building games | 1206 | Not measured | Only GLM 5.2 measured |
| Design Arena: HTML slides | 1175 | Not measured | Only GLM 5.2 measured |
| Design Arena: PowerPoint slides | 1195 | Not measured | Only GLM 5.2 measured |
| SREBench (Vals AI) | 0.0% | Not measured | Only GLM 5.2 measured |
| Finance Agent (Vals AI) | 49.7% | 35.8% | GLM 5.2 |
| Legal Research Bench (Vals AI) | 31.3% | 15.9% | GLM 5.2 |
| Excel Modeling Benchmark (Vals AI) | 61.5% | 28.5% | GLM 5.2 |
| τ²-Bench Telecom | 99.1% | 95.9% | GLM 5.2 |
| APEX-Agents | 45.2% | Not measured | Only GLM 5.2 measured |
| PostTrainBench | 31.7% | Not measured | Only GLM 5.2 measured |
| OSWorld | Not measured | 63.3% | Only Kimi K2.5 measured |
| Vending-Bench 2 | $8,314 | $1,198 | GLM 5.2 |
| Neither model has a result on the other 21 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index90
| Benchmark | GLM 5.2 | Kimi K2.5 | Leader |
|---|---|---|---|
| GPQA Diamond | 85.6% | 84.1% | GLM 5.2 |
| MMMU Pro (Vals AI) | Not measured | 84.3% | Only Kimi K2.5 measured |
| GPQA Diamond (Artificial Analysis run) | 89.5% | 87.9% | GLM 5.2 |
| Humanity's Last Exam (Artificial Analysis run) | 41.1% | 30.7% | GLM 5.2 |
| GPQA Diamond (Epoch AI run) | 91.9% | Not measured | Only GLM 5.2 measured |
| ARC-AGI | 77.0% | 65.3% | GLM 5.2 |
| ARC-AGI-2 | 22.8% | 11.8% | GLM 5.2 |
| SimpleBench | 58.8% | 46.8% | GLM 5.2 |
| Chess puzzles | 22.0% | Not measured | Only GLM 5.2 measured |
| Mystery game puzzles | 19.0% | Not measured | Only GLM 5.2 measured |
| EBR-bench | 9.5% | Not measured | Only GLM 5.2 measured |
| LMArena Text: hard prompts | 1481 | 1453 | GLM 5.2 |
| LMArena Text: expert | 1487 | 1466 | GLM 5.2 |
| LMArena Text: hard prompts in English | 1481 | 1460 | GLM 5.2 |
| LMArena Vision: diagrams | Not measured | 1282 | Only Kimi K2.5 measured |
| LMArena Vision: homework | Not measured | 1297 | Only Kimi K2.5 measured |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GLM 5.2 | Kimi K2.5 | Leader |
|---|---|---|---|
| AIME | Not measured | 95.6% | Only Kimi K2.5 measured |
| OTIS Mock AIME | 86.4% | Not measured | Only GLM 5.2 measured |
| FrontierMath, tiers 1 to 3 | 59.2% | Not measured | Only GLM 5.2 measured |
| FrontierMath, tier 4 | 29.3% | Not measured | Only GLM 5.2 measured |
| ProofBench | 35.0% | Not measured | Only GLM 5.2 measured |
| LMArena Text: math | 1483 | 1470 | GLM 5.2 |
| LMArena Text: mathematical work | 1489 | 1473 | GLM 5.2 |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index63
| Benchmark | GLM 5.2 | Kimi K2.5 | Leader |
|---|---|---|---|
| MMLU Pro | 86.7% | 85.9% | GLM 5.2 |
| LegalBench (Vals AI) | 84.1% | Not measured | Only GLM 5.2 measured |
| CaseLaw (Vals AI) | Not measured | 58.7% | Only Kimi K2.5 measured |
| CorpFin (Vals AI) | 66.1% | 68.3% | Kimi K2.5 |
| TaxEval (Vals AI) | 73.3% | 74.2% | Kimi K2.5 |
| MortgageTax (Vals AI) | Not measured | 66.5% | Only Kimi K2.5 measured |
| MedQA (Vals AI) | Not measured | 94.4% | Only Kimi K2.5 measured |
| MedCode (Vals AI) | 40.8% | 39.3% | GLM 5.2 |
| SimpleQA Verified | 34.2% | 34.3% | Kimi K2.5 |
| LMArena Text: science | 1489 | 1459 | GLM 5.2 |
| LMArena Text: medicine and healthcare | 1475 | 1448 | GLM 5.2 |
| LMArena Text: legal and government | 1486 | 1441 | GLM 5.2 |
| LMArena Text: business and finance | 1451 | 1427 | GLM 5.2 |
| Neither model has a result on the other 4 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | GLM 5.2 | Kimi K2.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1285 | 1249 | GLM 5.2 |
| Design Arena: UI components | 1296 | 1236 | GLM 5.2 |
| Design Arena: game dev | 1268 | 1207 | GLM 5.2 |
| Design Arena: data viz | 1285 | 1219 | GLM 5.2 |
| Design Arena: 3D | 1288 | 1205 | GLM 5.2 |
| Design Arena: all code categories | 1288 | 1236 | GLM 5.2 |
| Design Arena: SVG | 1214 | 1149 | GLM 5.2 |
| Design Arena: ASCII art | 1190 | 1165 | GLM 5.2 |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index200
| Benchmark | GLM 5.2 | Kimi K2.5 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 49.9% | Only Kimi K2.5 measured |
| MedScribe (Vals AI) | 83.5% | 76.4% | GLM 5.2 |
| IFBench | 73.3% | 70.2% | GLM 5.2 |
| Long context reasoning (AA-LCR) | 78.3% | 78.0% | GLM 5.2 |
| DTBench | 93.6% | Not measured | Only GLM 5.2 measured |
| LMCA | 45.8% | Not measured | Only GLM 5.2 measured |
| Fiction.LiveBench | Not measured | 86.1% | Only Kimi K2.5 measured |
| CL-bench | Not measured | 19.3% | Only Kimi K2.5 measured |
| Surface Evolver Bench | 55.6% | Not measured | Only GLM 5.2 measured |
| CL-bench Life | Not measured | 13.2% | Only Kimi K2.5 measured |
| LMArena Text | 1470 | 1445 | GLM 5.2 |
| LMArena Text: instruction following | 1466 | 1431 | GLM 5.2 |
| LMArena Text: creative writing | 1463 | 1422 | GLM 5.2 |
| LMArena Vision | Not measured | 1269 | Only Kimi K2.5 measured |
| LMArena Text: English | 1475 | 1453 | GLM 5.2 |
| LMArena Text: non-English | 1459 | 1433 | GLM 5.2 |
| LMArena Text: Chinese | 1522 | 1494 | GLM 5.2 |
| LMArena Text: German | 1470 | 1441 | GLM 5.2 |
| LMArena Text: Japanese | 1450 | 1423 | GLM 5.2 |
| LMArena Text: Korean | 1440 | 1412 | GLM 5.2 |
| LMArena Text: French | 1479 | 1454 | GLM 5.2 |
| LMArena Text: Spanish | 1478 | 1450 | GLM 5.2 |
| LMArena Text: Russian | 1468 | 1435 | GLM 5.2 |
| LMArena Text: Polish | 1456 | 1445 | GLM 5.2 |
| LMArena Text: multi-turn | 1469 | 1444 | GLM 5.2 |
| LMArena Text: longer queries | 1480 | 1445 | GLM 5.2 |
| LMArena Text: writing and language | 1463 | 1425 | GLM 5.2 |
| LMArena Text: entertainment and media | 1450 | 1417 | GLM 5.2 |
| LMArena Vision: English | Not measured | 1274 | Only Kimi K2.5 measured |
| LMArena Vision: Chinese | Not measured | 1328 | Only Kimi K2.5 measured |
| LMArena Vision: reading text | Not measured | 1276 | Only Kimi K2.5 measured |
| LMArena Vision: humor | Not measured | 1284 | Only Kimi K2.5 measured |
| LMArena Vision: captioning | Not measured | 1257 | Only Kimi K2.5 measured |
| LMArena Vision: recognizing things | Not measured | 1285 | Only Kimi K2.5 measured |
| LMArena Vision: creative writing | Not measured | 1269 | Only Kimi K2.5 measured |
| Neither model has a result on the other 11 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GLM 5.2 | Kimi K2.5 | 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
Kimi K2.5 costs less
Repository review
50K input + 3K output tokens
GLM 5.2 costs less
Agent loop
200K input + 10K output tokens
GLM 5.2 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 | Z.ai GLM 5.2 | MoonshotAI Kimi K2.5 |
|---|---|---|
| Maker | Z.ai | Moonshot AI |
| Weights | Open weights | Open weights |
| Released | June 16, 2026 | January 27, 2026 |
| Context window | 1.05M | 262K |
| Input $/Mtok | $0.0341 | $0.50 |
| Output $/Mtok | $7.00 | $2.50 |
| Coding index | 57.7 | 58.5 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | $0.86 | $0.24 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GLM 5.2 better than Kimi K2.5 for coding?
GLM 5.2 and Kimi K2.5 are level for coding, 57.7 against 58.5 on the Vibe Coding Index, so price and context decide. Pick GLM 5.2 when the context window is larger, 1.05M against 262K tokens, or when what matters is LMArena WebDev or AA Coding Index, where it leads. Pick Kimi K2.5 when output tokens cost 2.8x less, or when a solved task costs $0.24 against $0.86.
Which is cheaper, GLM 5.2 or Kimi K2.5?
GLM 5.2 costs $0.0341 per million input tokens and $7.00 per million output tokens; Kimi K2.5 costs $0.50 and $2.50. Per solved SWE-bench Verified task, GLM 5.2 costs $0.86 and Kimi K2.5 $0.24.
Which has the bigger context window, GLM 5.2 or Kimi K2.5?
GLM 5.2, with 1.05M tokens against 262K.
How many benchmarks is the GLM 5.2 vs Kimi K2.5 comparison based on?
74 benchmarks have a result for both models as of October 21, 2026. GLM 5.2's coding index rests on 1 independent benchmark and Kimi K2.5's on 2. Where only one model has a result, the page says so instead of naming a winner.