GLM 5.3 vs Kimi K2.6
GLM 5.3 leads Kimi K2.6 on coding, 70.6 to 52.1 on the Vibe Coding Index, at about the same output price ($4.40 vs $4.00 per million). Updated October 21, 2026; 80 benchmarks have a result for both.
GLM 5.3 or Kimi K2.6: which to pick
Pick GLM 5.3 for coding: it scores 70.6 on the Vibe Coding Index against 52.1 for Kimi K2.6.
Pick Kimi K2.6 for output tokens 1.1x cheaper ($4.00 vs $4.40 per million) and a lower cost per solved task ($0.35 against $0.36).
- Shared results
- 80
- GLM 5.3 only
- 20
- Kimi K2.6 only
- 29
- 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
GLM 5.3
GLM 5.3 scores 70.6 against 52.1.
6 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
GLM 5.3
GLM 5.3 leads, 44.8 against 27.0.
Same board, both measured
Agentic work
AA Agentic Index
GLM 5.3
GLM 5.3 leads, 53.1 against 20.5.
Same board, both measured
Reasoning
GPQA Diamond
Kimi K2.6
Kimi K2.6 leads, 89.1% against 88.1%.
Same board, both measured
Knowledge
MMLU Pro
Kimi K2.6
Kimi K2.6 leads, 87.6% against 86.8%.
Same board, both measured
Web design
Design Arena: websites
GLM 5.3
GLM 5.3 leads, 1295 against 1269.
Same board, both measured
General
Vals Index
No call
Only GLM 5.3 has a Vals Index result, 59.7%.
Directional only
Long documents
Listed context window
GLM 5.3
GLM 5.3 takes 1.05M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Kimi K2.6
GLM 5.3 $0.0036, Kimi K2.6 $0.0029 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Kimi K2.6
GLM 5.3 $0.36, Kimi K2.6 $0.35.
Published attempt cost and pass rate
At a glance
- Coding index
- GLM 5.3 70.6 from 6 benchmarks, Kimi K2.6 52.1 from 3 benchmarks.
- Widest category
- Agentic work, 15.4 points apart on average over 9 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): GLM 5.3 78.1% against Kimi K2.6 37.9%, 40.2 points apart on a 0 to 100 scale.
- Output price
- GLM 5.3 $4.40 against Kimi K2.6 $4.00 per million output tokens, 1.1x apart.
- Context window
- GLM 5.3 takes 1.05M tokens, Kimi K2.6 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 5.3 | Bars | Kimi K2.6 | Ties |
|---|---|---|---|---|
| Coding | 14 | 1 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 8 | 1 | ||
| Reasoning | 8 | 1 | ||
| Math | 5 | 1 | ||
| Knowledge | 7 | 2 | ||
| Web design | 8 | 0 | ||
| General | 19 | 3 | ||
| All shared boards | 71 | 9 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index141
| Benchmark | GLM 5.3 | Kimi K2.6 | Leader |
|---|---|---|---|
| LiveBench coding | 82.8% | Not measured | Only GLM 5.3 measured |
| LMArena WebDev | 1621 | 1509 | GLM 5.3 |
| AA Coding Index | 74.8 | 61.8 | GLM 5.3 |
| LiveCodeBench (Vals AI) | 80.5% | 86.8% | Kimi K2.6 |
| SWE-bench Verified (Vals AI) | 95.4% | 76.2% | GLM 5.3 |
| Terminal-Bench 4 (Vals AI) | 38.9% | Not measured | Only GLM 5.3 measured |
| Vibe Code Bench (Vals AI) | 78.1% | 37.9% | GLM 5.3 |
| Code migration (Vals AI) | 44.2% | 27.8% | GLM 5.3 |
| ProgramBench (Vals AI) | 1.5% | 0.0% | GLM 5.3 |
| IOI (Vals AI) | 68.4% | Not measured | Only GLM 5.3 measured |
| Terminal-Bench 2.1 (Vals AI) | 71.5% | 53.6% | GLM 5.3 |
| Vibe Code Bench 1-100 (Vals AI) | 20.0% | Not measured | Only GLM 5.3 measured |
| SkillsBench (Vals AI) | 47.5% | Not measured | Only GLM 5.3 measured |
| CyberBench (Vals AI) | 72.1% | Not measured | Only GLM 5.3 measured |
| SciCode | 59.0% | 51.5% | GLM 5.3 |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 43.9% | Only Kimi K2.6 measured |
| FrontierCode | 40.1% | Not measured | Only GLM 5.3 measured |
| FrontierSWE | 30.2% | Not measured | Only GLM 5.3 measured |
| WeirdML | 75.4% | 55.9% | GLM 5.3 |
| ALE-Bench | 1317.4 | 1092.7 | GLM 5.3 |
| LMArena Text: coding | 1497 | 1489 | GLM 5.3 |
| LMArena Text: software and IT | 1493 | 1484 | GLM 5.3 |
| LMArena WebDev: React | 1641 | 1505 | GLM 5.3 |
| LMArena WebDev: HTML | 1595 | 1485 | GLM 5.3 |
| LMArena WebDev: from an image | Not measured | 1521 | Only Kimi K2.6 measured |
| Neither model has a result on the other 14 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GLM 5.3 | Kimi K2.6 | Leader |
|---|---|---|---|
| AA Intelligence Index | 44.8 | 27.0 | GLM 5.3 |
| Epoch Capabilities Index | 156.0 | 150.9 | GLM 5.3 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index81
| Benchmark | GLM 5.3 | Kimi K2.6 | Leader |
|---|---|---|---|
| AA Agentic Index | 53.1 | 20.5 | GLM 5.3 |
| Design Arena: agents building web apps | Not measured | 1268 | Only Kimi K2.6 measured |
| Design Arena: agents building full-stack apps | Not measured | 1155 | Only Kimi K2.6 measured |
| Design Arena: agents building mobile apps | 1194 | 1157 | GLM 5.3 |
| Design Arena: agents building Android apps | Not measured | 1160 | Only Kimi K2.6 measured |
| Design Arena: agents building Godot games | Not measured | 1120 | Only Kimi K2.6 measured |
| Design Arena: agents building games | Not measured | 1141 | Only Kimi K2.6 measured |
| Design Arena: HTML slides | 1189 | 1184 | GLM 5.3 |
| Design Arena: PowerPoint slides | 1254 | 1128 | GLM 5.3 |
| Design Arena: spreadsheets | Not measured | 1276 | Only Kimi K2.6 measured |
| LiveBench research | 73.2% | Not measured | Only GLM 5.3 measured |
| LiveBench browser | 0.0% | Not measured | Only GLM 5.3 measured |
| LiveBench long agentic | 35.9% | Not measured | Only GLM 5.3 measured |
| SREBench (Vals AI) | 9.2% | Not measured | Only GLM 5.3 measured |
| Finance Agent (Vals AI) | 55.8% | 44.9% | GLM 5.3 |
| Tax Agent Bench (Vals AI) | 39.7% | 12.4% | GLM 5.3 |
| Legal Research Bench (Vals AI) | 49.0% | 15.9% | GLM 5.3 |
| Harvey's Legal Agent Benchmark (Vals AI) | 14.6% | Not measured | Only GLM 5.3 measured |
| Excel Modeling Benchmark (Vals AI) | 56.3% | 57.9% | Kimi K2.6 |
| Terminal-Bench-Science (Vals AI) | 5.7% | Not measured | Only GLM 5.3 measured |
| τ²-Bench Telecom | Not measured | 95.9% | Only Kimi K2.6 measured |
| APEX-Agents | 56.6% | Not measured | Only GLM 5.3 measured |
| OSWorld 2.0 | Not measured | 4.6% | Only Kimi K2.6 measured |
| Vending-Bench 2 | $8,164 | $6,205 | GLM 5.3 |
| Neither model has a result on the other 17 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index81
| Benchmark | GLM 5.3 | Kimi K2.6 | Leader |
|---|---|---|---|
| GPQA Diamond | 88.1% | 89.1% | Kimi K2.6 |
| LiveBench reasoning | 85.8% | Not measured | Only GLM 5.3 measured |
| MysteryMechanism (Vals AI) | 23.0% | Not measured | Only GLM 5.3 measured |
| MMMU Pro (Vals AI) | Not measured | 86.3% | Only Kimi K2.6 measured |
| GPQA Diamond (Artificial Analysis run) | 91.7% | 91.1% | GLM 5.3 |
| Humanity's Last Exam (Artificial Analysis run) | 42.3% | 37.5% | GLM 5.3 |
| GPQA Diamond (Epoch AI run) | 90.9% | 90.8% | GLM 5.3 |
| Chess puzzles | 37.0% | 20.0% | GLM 5.3 |
| Mystery game puzzles | 33.0% | 18.0% | GLM 5.3 |
| EBR-bench | Not measured | 2.4% | Only Kimi K2.6 measured |
| LMArena Text: hard prompts | 1490 | 1470 | GLM 5.3 |
| LMArena Text: expert | 1514 | 1491 | GLM 5.3 |
| LMArena Text: hard prompts in English | 1496 | 1471 | GLM 5.3 |
| LMArena Vision: diagrams | Not measured | 1298 | Only Kimi K2.6 measured |
| LMArena Vision: homework | Not measured | 1310 | Only Kimi K2.6 measured |
| Neither model has a result on the other 7 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index51
| Benchmark | GLM 5.3 | Kimi K2.6 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 91.1% | 96.1% | Kimi K2.6 |
| FrontierMath, tiers 1 to 3 | 68.8% | 57.2% | GLM 5.3 |
| FrontierMath, tier 4 | 29.3% | 25.6% | GLM 5.3 |
| ProofBench | 49.0% | 16.0% | GLM 5.3 |
| LMArena Text: math | 1495 | 1474 | GLM 5.3 |
| LMArena Text: mathematical work | 1497 | 1480 | GLM 5.3 |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index72
| Benchmark | GLM 5.3 | Kimi K2.6 | Leader |
|---|---|---|---|
| MMLU Pro | 86.8% | 87.6% | Kimi K2.6 |
| LegalBench (Vals AI) | 84.8% | 84.7% | GLM 5.3 |
| CaseLaw (Vals AI) | Not measured | 61.2% | Only Kimi K2.6 measured |
| CorpFin (Vals AI) | Not measured | 66.7% | Only Kimi K2.6 measured |
| TaxEval (Vals AI) | 72.4% | 74.7% | Kimi K2.6 |
| MortgageTax (Vals AI) | Not measured | 65.8% | Only Kimi K2.6 measured |
| MedCode (Vals AI) | 42.9% | 40.1% | GLM 5.3 |
| SimpleQA Verified | 41.0% | 34.9% | GLM 5.3 |
| LMArena Text: science | 1498 | 1468 | GLM 5.3 |
| LMArena Text: medicine and healthcare | 1481 | 1457 | GLM 5.3 |
| LMArena Text: legal and government | 1473 | 1462 | GLM 5.3 |
| LMArena Text: business and finance | 1459 | 1445 | GLM 5.3 |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | GLM 5.3 | Kimi K2.6 | Leader |
|---|---|---|---|
| Design Arena: websites | 1295 | 1269 | GLM 5.3 |
| Design Arena: UI components | 1314 | 1266 | GLM 5.3 |
| Design Arena: game dev | 1311 | 1251 | GLM 5.3 |
| Design Arena: data viz | 1259 | 1249 | GLM 5.3 |
| Design Arena: 3D | 1332 | 1268 | GLM 5.3 |
| Design Arena: all code categories | 1304 | 1272 | GLM 5.3 |
| Design Arena: SVG | 1293 | 1181 | GLM 5.3 |
| Design Arena: ASCII art | 1213 | 1165 | GLM 5.3 |
| LiveBench design | 77.3% | Not measured | Only GLM 5.3 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index193
| Benchmark | GLM 5.3 | Kimi K2.6 | Leader |
|---|---|---|---|
| Vals Index | 59.7% | Not measured | Only GLM 5.3 measured |
| LiveBench data analysis | 70.2% | Not measured | Only GLM 5.3 measured |
| Public Benefits Bench (Vals AI) | 68.5% | 56.6% | GLM 5.3 |
| SAGE (Vals AI) | Not measured | 50.2% | Only Kimi K2.6 measured |
| MedScribe (Vals AI) | 88.8% | 78.2% | GLM 5.3 |
| Vals Multimodal Index | Not measured | 56.4% | Only Kimi K2.6 measured |
| IFBench | Not measured | 76.0% | Only Kimi K2.6 measured |
| Long context reasoning (AA-LCR) | 79.7% | 81.0% | Kimi K2.6 |
| DTBench | 87.7% | 90.9% | Kimi K2.6 |
| LMCA | 55.5% | 37.3% | GLM 5.3 |
| Furniture assembly | Not measured | 21.7% | Only Kimi K2.6 measured |
| ExploitBench | Not measured | 18.4% | Only Kimi K2.6 measured |
| LMArena Text | 1474 | 1455 | GLM 5.3 |
| LMArena Text: instruction following | 1479 | 1451 | GLM 5.3 |
| LMArena Text: creative writing | 1458 | 1434 | GLM 5.3 |
| LMArena Vision | Not measured | 1282 | Only Kimi K2.6 measured |
| LMArena Text: English | 1482 | 1460 | GLM 5.3 |
| LMArena Text: non-English | 1459 | 1446 | GLM 5.3 |
| LMArena Text: Chinese | 1532 | 1520 | GLM 5.3 |
| LMArena Text: German | 1488 | 1451 | GLM 5.3 |
| LMArena Text: Japanese | 1460 | 1443 | GLM 5.3 |
| LMArena Text: Korean | 1460 | 1427 | GLM 5.3 |
| LMArena Text: French | 1503 | 1471 | GLM 5.3 |
| LMArena Text: Spanish | 1462 | 1464 | Kimi K2.6 |
| LMArena Text: Russian | 1469 | 1446 | GLM 5.3 |
| LMArena Text: Polish | 1466 | 1438 | GLM 5.3 |
| LMArena Text: multi-turn | 1472 | 1453 | GLM 5.3 |
| LMArena Text: longer queries | 1483 | 1468 | GLM 5.3 |
| LMArena Text: writing and language | 1469 | 1439 | GLM 5.3 |
| LMArena Text: entertainment and media | 1447 | 1428 | GLM 5.3 |
| LMArena Vision: English | Not measured | 1287 | Only Kimi K2.6 measured |
| LMArena Vision: Chinese | Not measured | 1346 | Only Kimi K2.6 measured |
| LMArena Vision: reading text | Not measured | 1291 | Only Kimi K2.6 measured |
| LMArena Vision: humor | Not measured | 1280 | Only Kimi K2.6 measured |
| LMArena Vision: creative writing | Not measured | 1273 | Only Kimi K2.6 measured |
| LMArena Document | Not measured | 1451 | Only Kimi K2.6 measured |
| Neither model has a result on the other 10 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GLM 5.3 | Kimi K2.6 | 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 K2.6 costs less
Repository review
50K input + 3K output tokens
Kimi K2.6 costs less
Agent loop
200K input + 10K output tokens
Kimi K2.6 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 5.3 | MoonshotAI Kimi K2.6 |
|---|---|---|
| Maker | Z.ai | Moonshot AI |
| Weights | Open weights | Open weights |
| Released | August 18, 2026 | April 20, 2026 |
| Context window | 1.05M | 262K |
| Input $/Mtok | $1.40 | $0.95 |
| Output $/Mtok | $4.40 | $4.00 |
| Coding index | 70.6 | 52.1 |
| Independent measurements behind it | 6 | 3 |
| Cost per solved task | $0.36 | $0.35 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GLM 5.3 better than Kimi K2.6 for coding?
Pick GLM 5.3 for coding: it scores 70.6 on the Vibe Coding Index against 52.1 for Kimi K2.6. Pick Kimi K2.6 for output tokens 1.1x cheaper ($4.00 vs $4.40 per million) and a lower cost per solved task ($0.35 against $0.36).
Which is cheaper, GLM 5.3 or Kimi K2.6?
GLM 5.3 costs $1.40 per million input tokens and $4.40 per million output tokens; Kimi K2.6 costs $0.95 and $4.00. Per solved SWE-bench Verified task, GLM 5.3 costs $0.36 and Kimi K2.6 $0.35.
Which has the bigger context window, GLM 5.3 or Kimi K2.6?
GLM 5.3, with 1.05M tokens against 262K.
How many benchmarks is the GLM 5.3 vs Kimi K2.6 comparison based on?
80 benchmarks have a result for both models as of October 21, 2026. GLM 5.3's coding index rests on 6 independent benchmarks and Kimi K2.6's on 3. Where only one model has a result, the page says so instead of naming a winner.