Model comparison
GLM-5.2 vs Kimi K2.6
GLM-5.2 is the stronger model overall, scoring 51.1 to 47.7 on the Noometry Index.
Last verified . 41 shared benchmarks.
Summary
- They share 41 benchmarks with published results for both. GLM-5.2 scores higher in 8 categories and Kimi K2.6 in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GLM-5.2 leads 32.4 to 21.9.
- The biggest single-benchmark swing is ProofBench: 35% for GLM-5.2 and 16% for Kimi K2.6.
- Kimi K2.6 is cheaper at $0.95 / $4 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
- GLM-5.2 accepts more context: 1M tokens versus 262K.
Side by side
| GLM-5.2 | Kimi K2.6 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Moonshot AI |
| Noometry Index | 51.1 | 47.7 |
| Released | 2026-06-13 | 2026-04-20 |
| Weights | Open | Open |
| Context window | 1M | 262K |
| Max output | 131K | 262K |
| Input $ / M tokens | $1.40 | $0.95 |
| Output $ / M tokens | $4.40 | $4 |
| Results tracked | 51 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-5.2: 51.3 (#41), Kimi K2.6: 50.7 (#43)
| Benchmark | GLM-5.2 | Kimi K2.6 |
|---|---|---|
| SWE-bench Verified | 78.7% | 76.7% |
| LMArena WebDev | 1603 | 1509 |
| SciCode | 50.5% | 53.5% |
| WeirdML | 70.1% | 55.9% |
| LMArena Coding | 1485 | 1488 |
| ALE-Bench | 1,047 | 1,093 |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
Agentic & Tool Use GLM-5.2 leads
GLM-5.2: 32.4 (#63), Kimi K2.6: 21.9 (#137)
| Benchmark | GLM-5.2 | Kimi K2.6 |
|---|---|---|
| GBAEval | 0% | 0.9% |
| Vending-Bench 2 | 8,314 | 6,205 |
| APEX-Agents | 45.2% | — |
| OSWorld 2.0 | — | 4.6% |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| ExploitBench | — | 18.4% |
| GDP.pdf | — | 12% |
Reasoning GLM-5.2 leads
GLM-5.2: 42.3 (#52), Kimi K2.6: 40.5 (#55)
| Benchmark | GLM-5.2 | Kimi K2.6 |
|---|---|---|
| NYT Connections (extended) | 74.3% | 87.2% |
| CritPt | 20.9% | 8% |
| Chess Puzzles | 21% | 26% |
| EBR-Bench | 9.5% | 2.4% |
| LMArena Hard Prompts | 1480 | 1470 |
| Mystery Game Puzzles | 19% | 18% |
| DTBench | 93.6% | 90.9% |
| LMCA | 45.8% | 37.3% |
| Epoch Capabilities Index | 151.78 | 151.05 |
| ARC-AGI-2 | 22.8% | — |
| SimpleBench | 58.8% | — |
| Kagi LLM Benchmark | 62.6% | — |
| ARC-AGI-1 | 77% | — |
| Surface Evolver Bench | 55.6% | — |
Math Kimi K2.6 leads
GLM-5.2: 55.7 (#43), Kimi K2.6: 57.0 (#41)
| Benchmark | GLM-5.2 | Kimi K2.6 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 59.2% | 57.2% |
| FrontierMath Tier 4 | 29.3% | 25.6% |
| MathArena Final-Answer Competitions | 67.6% | 72.9% |
| OTIS Mock AIME 2024-2025 | 86.4% | 96.1% |
| ProofBench | 35% | 16% |
| LMArena Math | 1482 | 1475 |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#40), Kimi K2.6: 54.0 (#54)
| Benchmark | GLM-5.2 | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | 91.9% | 90.8% |
| SimpleQA Verified | 34.2% | 34.9% |
| LMArena Expert | 1486 | 1491 |
| Vectara Hallucination Rate | — | 10.8% |
Multimodal Not comparable
GLM-5.2: —, Kimi K2.6: 31.6 (#103)
| Benchmark | GLM-5.2 | Kimi K2.6 |
|---|---|---|
| LMArena Vision | — | 1283 |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual Too close to call
GLM-5.2: 55.8 (#26), Kimi K2.6: 54.9 (#37)
| Benchmark | GLM-5.2 | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1459 | 1446 |
| LMArena Chinese | 1519 | 1521 |
| LMArena French | 1479 | 1471 |
| LMArena German | 1468 | 1450 |
| LMArena Japanese | 1451 | 1443 |
| LMArena Korean | 1445 | 1427 |
| LMArena Russian | 1466 | 1446 |
| LMArena Spanish | 1477 | 1464 |
Instruction Following Too close to call
GLM-5.2: 76.9 (#34), Kimi K2.6: 76.3 (#43)
| Benchmark | GLM-5.2 | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1465 | 1451 |
Long Context Too close to call
GLM-5.2: 45.3 (#43), Kimi K2.6: 44.9 (#52)
| Benchmark | GLM-5.2 | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1479 | 1468 |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.4 (#21), Kimi K2.6: 68.5 (#26)
| Benchmark | GLM-5.2 | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1470 | 1455 |
| LMArena Creative Writing | 1462 | 1434 |
| EQ-Bench Creative Writing | 1757 | 1725 |
| EQ-Bench 4 | 1222 | 1202 |
| LMArena Multi-Turn | 1469 | 1453 |
Frequently asked questions
Is GLM-5.2 better than Kimi K2.6?
GLM-5.2 is the stronger model overall, scoring 51.1 to 47.7 on the Noometry Index.
Which is cheaper, GLM-5.2 or Kimi K2.6?
Kimi K2.6 is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; GLM-5.2 lists at $1.40 and $4.40.
Is GLM-5.2 or Kimi K2.6 better for coding?
They score almost the same on coding (51.3 vs 50.7); test both on your own repository before choosing.
Which has the bigger context window?
GLM-5.2 does, with 1M tokens against 262K.
How many benchmarks do GLM-5.2 and Kimi K2.6 share?
41 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and Kimi K2.6 has 51.