Model comparison
GLM-5 vs Kimi K2.6
Kimi K2.6 is the stronger model overall, scoring 47.7 to 46.1 on the Noometry Index.
Last verified . 32 shared benchmarks.
Summary
- They share 32 benchmarks with published results for both. GLM-5 scores higher in 1 category and Kimi K2.6 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.6 leads 40.5 to 27.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 80% for GLM-5 and 96.1% for Kimi K2.6.
- GLM-5 is cheaper at $1 / $3.20 per million input/output tokens, against $0.95 / $4 for Kimi K2.6.
- Kimi K2.6 accepts more context: 262K tokens versus 205K.
Side by side
| GLM-5 | Kimi K2.6 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Moonshot AI |
| Noometry Index | 46.1 | 47.7 |
| Released | 2026-02-11 | 2026-04-20 |
| Weights | Open | Open |
| Context window | 205K | 262K |
| Max output | 131K | 262K |
| Input $ / M tokens | $1 | $0.95 |
| Output $ / M tokens | $3.20 | $4 |
| Results tracked | 45 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
GLM-5: 49.0 (#52), Kimi K2.6: 50.7 (#43)
| Benchmark | GLM-5 | Kimi K2.6 |
|---|---|---|
| SWE-bench Verified | 72.1% | 76.7% |
| LMArena WebDev | 1434 | 1509 |
| WeirdML | 48.2% | 55.9% |
| LMArena Coding | 1461 | 1488 |
| ALE-Bench | 765.62 | 1,093 |
| SWE-bench Verified (bash only) | 72.8% | — |
| SWE-bench Multilingual | 69.7% | — |
| SciCode | — | 53.5% |
Agentic & Tool Use GLM-5 leads
GLM-5: 31.1 (#71), Kimi K2.6: 21.9 (#137)
| Benchmark | GLM-5 | Kimi K2.6 |
|---|---|---|
| Vending-Bench 2 | 4,432 | 6,205 |
| Terminal-Bench | 52.4% | — |
| OSWorld 2.0 | — | 4.6% |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
Reasoning Kimi K2.6 leads
GLM-5: 27.6 (#116), Kimi K2.6: 40.5 (#55)
| Benchmark | GLM-5 | Kimi K2.6 |
|---|---|---|
| NYT Connections (extended) | 74.8% | 87.2% |
| Chess Puzzles | 10% | 26% |
| LMArena Hard Prompts | 1452 | 1470 |
| Epoch Capabilities Index | 145.83 | 151.05 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 53.2% | — |
| Kagi LLM Benchmark | 75% | — |
| ARC-AGI-1 | 44.7% | — |
| CritPt | — | 8% |
| EBR-Bench | — | 2.4% |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 90.9% |
| LMCA | — | 37.3% |
| ForecastBench | 61 | — |
Math Kimi K2.6 leads
GLM-5: 46.4 (#71), Kimi K2.6: 57.0 (#41)
| Benchmark | GLM-5 | Kimi K2.6 |
|---|---|---|
| MathArena Final-Answer Competitions | 65.7% | 72.9% |
| OTIS Mock AIME 2024-2025 | 80% | 96.1% |
| LMArena Math | 1440 | 1475 |
| FrontierMath (Feb 2025 set) | 16.4% | 39% |
| FrontierMath Tier 4 (v1) | 2.1% | 14.6% |
| FrontierMath (Tiers 1-3) | — | 57.2% |
| FrontierMath Tier 4 | — | 25.6% |
| ProofBench | — | 16% |
Knowledge Kimi K2.6 leads
GLM-5: 52.3 (#64), Kimi K2.6: 54.0 (#54)
| Benchmark | GLM-5 | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | 87.8% | 90.8% |
| Vectara Hallucination Rate | 10.1% | 10.8% |
| LMArena Expert | 1454 | 1491 |
| SimpleQA Verified | — | 34.9% |
Multimodal Not comparable
GLM-5: —, Kimi K2.6: 31.6 (#103)
| Benchmark | GLM-5 | Kimi K2.6 |
|---|---|---|
| LMArena Vision | — | 1283 |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual Kimi K2.6 leads
GLM-5: 53.7 (#58), Kimi K2.6: 54.9 (#37)
| Benchmark | GLM-5 | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1430 | 1446 |
| LMArena Chinese | 1511 | 1521 |
| LMArena French | 1455 | 1471 |
| LMArena German | 1445 | 1450 |
| LMArena Japanese | 1416 | 1443 |
| LMArena Korean | 1423 | 1427 |
| LMArena Russian | 1436 | 1446 |
| LMArena Spanish | 1454 | 1464 |
Instruction Following Kimi K2.6 leads
GLM-5: 75.2 (#67), Kimi K2.6: 76.3 (#43)
| Benchmark | GLM-5 | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1428 | 1451 |
Long Context Too close to call
GLM-5: 44.7 (#60), Kimi K2.6: 44.9 (#52)
| Benchmark | GLM-5 | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1446 | 1468 |
| CL-bench | 18.7% | — |
Writing & Preference Kimi K2.6 leads
GLM-5: 66.0 (#38), Kimi K2.6: 68.5 (#26)
| Benchmark | GLM-5 | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1446 | 1455 |
| LMArena Creative Writing | 1439 | 1434 |
| EQ-Bench Creative Writing | 1601 | 1725 |
| LMArena Multi-Turn | 1456 | 1453 |
| EQ-Bench 4 | — | 1202 |
Frequently asked questions
Is GLM-5 better than Kimi K2.6?
Kimi K2.6 is the stronger model overall, scoring 47.7 to 46.1 on the Noometry Index.
Which is cheaper, GLM-5 or Kimi K2.6?
GLM-5 is cheaper. It lists at $1 per million input tokens and $3.20 per million output tokens; Kimi K2.6 lists at $0.95 and $4.
Is GLM-5 or Kimi K2.6 better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 49.0 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.6 does, with 262K tokens against 205K.
How many benchmarks do GLM-5 and Kimi K2.6 share?
32 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Kimi K2.6 has 51.