Model comparison
GLM-5.3-Flash vs Kimi K2.6
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 47.7 on the Noometry Index.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. GLM-5.3-Flash scores higher in 8 categories and Kimi K2.6 in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GLM-5.3-Flash leads 34.2 to 21.9.
- The biggest single-benchmark swing is Chess Puzzles: 14% for GLM-5.3-Flash and 26% for Kimi K2.6.
- GLM-5.3-Flash is cheaper at $0.15 / $0.50 per million input/output tokens, against $0.95 / $4 for Kimi K2.6.
- GLM-5.3-Flash accepts more context: 1M tokens versus 262K.
Side by side
| GLM-5.3-Flash | Kimi K2.6 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Moonshot AI |
| Noometry Index | 51.8 | 47.7 |
| Released | 2026-08-20 | 2026-04-20 |
| Weights | Open | Open |
| Context window | 1M | 262K |
| Max output | 131K | 262K |
| Input $ / M tokens | $0.15 | $0.95 |
| Output $ / M tokens | $0.50 | $4 |
| Results tracked | 40 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3-Flash leads
GLM-5.3-Flash: 53.1 (#31), Kimi K2.6: 50.7 (#43)
| Benchmark | GLM-5.3-Flash | Kimi K2.6 |
|---|---|---|
| LMArena WebDev | 1609 | 1509 |
| SciCode | 51.6% | 53.5% |
| LMArena Coding | 1508 | 1488 |
| ALE-Bench | 303.55 | 1,093 |
| SWE-bench Verified | — | 76.7% |
| DeepSWE | 63.4% | — |
| FrontierCode | 31.8% | — |
| CursorBench | 36.8% | — |
| FrontierSWE | 18.1% | — |
| WeirdML | — | 55.9% |
Agentic & Tool Use GLM-5.3-Flash leads
GLM-5.3-Flash: 34.2 (#47), Kimi K2.6: 21.9 (#137)
| Benchmark | GLM-5.3-Flash | Kimi K2.6 |
|---|---|---|
| GDP.pdf | 14% | 12% |
| APEX-Agents | 52.8% | — |
| OSWorld 2.0 | — | 4.6% |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 6,205 |
Reasoning GLM-5.3-Flash leads
GLM-5.3-Flash: 48.0 (#42), Kimi K2.6: 40.5 (#55)
| Benchmark | GLM-5.3-Flash | Kimi K2.6 |
|---|---|---|
| CritPt | 15.4% | 8% |
| Chess Puzzles | 14% | 26% |
| LMArena Hard Prompts | 1491 | 1470 |
| Mystery Game Puzzles | 8% | 18% |
| Epoch Capabilities Index | 151.88 | 151.05 |
| ARC-AGI-2 | 65.8% | — |
| NYT Connections (extended) | — | 87.2% |
| ARC-AGI-1 | 91% | — |
| EBR-Bench | — | 2.4% |
| DTBench | — | 90.9% |
| LMCA | — | 37.3% |
| Surface Evolver Bench | 52.5% | — |
| Bench to the Future 3 | 0.15 | — |
Math Kimi K2.6 leads
GLM-5.3-Flash: 53.3 (#47), Kimi K2.6: 57.0 (#41)
| Benchmark | GLM-5.3-Flash | Kimi K2.6 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.8% | 57.2% |
| FrontierMath Tier 4 | 17.1% | 25.6% |
| OTIS Mock AIME 2024-2025 | 93.9% | 96.1% |
| ProofBench | 21% | 16% |
| LMArena Math | 1500 | 1475 |
| MathArena Final-Answer Competitions | — | 72.9% |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge GLM-5.3-Flash leads
GLM-5.3-Flash: 58.4 (#36), Kimi K2.6: 54.0 (#54)
| Benchmark | GLM-5.3-Flash | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | 90.2% | 90.8% |
| LMArena Expert | 1513 | 1491 |
| SimpleQA Verified | — | 34.9% |
| Vectara Hallucination Rate | — | 10.8% |
Multimodal GLM-5.3-Flash leads
GLM-5.3-Flash: 42.8 (#27), Kimi K2.6: 31.6 (#103)
| Benchmark | GLM-5.3-Flash | Kimi K2.6 |
|---|---|---|
| LMArena Vision | 1296 | 1283 |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual GLM-5.3-Flash leads
GLM-5.3-Flash: 56.0 (#25), Kimi K2.6: 54.9 (#37)
| Benchmark | GLM-5.3-Flash | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1462 | 1446 |
| LMArena Chinese | 1527 | 1521 |
| LMArena French | 1496 | 1471 |
| LMArena German | 1470 | 1450 |
| LMArena Japanese | 1429 | 1443 |
| LMArena Korean | 1446 | 1427 |
| LMArena Russian | 1469 | 1446 |
| LMArena Spanish | 1471 | 1464 |
Instruction Following GLM-5.3-Flash leads
GLM-5.3-Flash: 77.5 (#20), Kimi K2.6: 76.3 (#43)
| Benchmark | GLM-5.3-Flash | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1478 | 1451 |
Long Context Too close to call
GLM-5.3-Flash: 45.4 (#39), Kimi K2.6: 44.9 (#52)
| Benchmark | GLM-5.3-Flash | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1482 | 1468 |
Writing & Preference Kimi K2.6 leads
GLM-5.3-Flash: 65.3 (#50), Kimi K2.6: 68.5 (#26)
| Benchmark | GLM-5.3-Flash | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1471 | 1455 |
| LMArena Creative Writing | 1442 | 1434 |
| LMArena Multi-Turn | 1467 | 1453 |
| EQ-Bench Creative Writing | — | 1725 |
| EQ-Bench 4 | — | 1202 |
Frequently asked questions
Is GLM-5.3-Flash better than Kimi K2.6?
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 47.7 on the Noometry Index.
Which is cheaper, GLM-5.3-Flash or Kimi K2.6?
GLM-5.3-Flash is cheaper. It lists at $0.15 per million input tokens and $0.50 per million output tokens; Kimi K2.6 lists at $0.95 and $4.
Is GLM-5.3-Flash or Kimi K2.6 better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.1 versus 50.7 in the Noometry coding category.
Which has the bigger context window?
GLM-5.3-Flash does, with 1M tokens against 262K.
How many benchmarks do GLM-5.3-Flash and Kimi K2.6 share?
31 benchmarks have published results for both models. GLM-5.3-Flash has 40 scored results on Noometry and Kimi K2.6 has 51.