Model comparison
GLM-4.7 vs Kimi K2.6
Kimi K2.6 is the stronger model overall, scoring 47.7 to 42.0 on the Noometry Index. GLM-4.7 costs 1.7× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.
Last verified . 32 shared benchmarks.
Summary
- They share 32 benchmarks with published results for both. GLM-4.7 scores higher in 1 category and Kimi K2.6 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.6 leads 57.0 to 38.6.
- The biggest single-benchmark swing is Chess Puzzles: 6% for GLM-4.7 and 26% for Kimi K2.6.
- GLM-4.7 is cheaper at $0.60 / $2.20 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-4.7 | Kimi K2.6 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Moonshot AI |
| Noometry Index | 42.0 | 47.7 |
| Released | 2025-12-22 | 2026-04-20 |
| Weights | Open | Open |
| Context window | 205K | 262K |
| Max output | 131K | 262K |
| Input $ / M tokens | $0.60 | $0.95 |
| Output $ / M tokens | $2.20 | $4 |
| Results tracked | 36 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
GLM-4.7: 44.0 (#79), Kimi K2.6: 50.7 (#43)
| Benchmark | GLM-4.7 | Kimi K2.6 |
|---|---|---|
| LMArena WebDev | 1435 | 1509 |
| SciCode | 45.1% | 53.5% |
| LMArena Coding | 1454 | 1488 |
| ALE-Bench | 399.48 | 1,093 |
| SWE-bench Verified | — | 76.7% |
| WeirdML | — | 55.9% |
Agentic & Tool Use GLM-4.7 leads
GLM-4.7: 26.5 (#103), Kimi K2.6: 21.9 (#137)
| Benchmark | GLM-4.7 | Kimi K2.6 |
|---|---|---|
| Vending-Bench 2 | 2,377 | 6,205 |
| Terminal-Bench | 33.4% | — |
| OSWorld 2.0 | — | 4.6% |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
Reasoning Kimi K2.6 leads
GLM-4.7: 24.3 (#164), Kimi K2.6: 40.5 (#55)
| Benchmark | GLM-4.7 | Kimi K2.6 |
|---|---|---|
| CritPt | 1.7% | 8% |
| Chess Puzzles | 6% | 26% |
| LMArena Hard Prompts | 1443 | 1470 |
| Epoch Capabilities Index | 143.51 | 151.05 |
| SimpleBench | 47.7% | — |
| NYT Connections (extended) | — | 87.2% |
| EBR-Bench | — | 2.4% |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 90.9% |
| LMCA | — | 37.3% |
Math Kimi K2.6 leads
GLM-4.7: 38.6 (#135), Kimi K2.6: 57.0 (#41)
| Benchmark | GLM-4.7 | Kimi K2.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 96.1% |
| ProofBench | 6% | 16% |
| LMArena Math | 1423 | 1475 |
| FrontierMath (Feb 2025 set) | 2.4% | 39% |
| FrontierMath Tier 4 (v1) | 0% | 14.6% |
| FrontierMath (Tiers 1-3) | — | 57.2% |
| FrontierMath Tier 4 | — | 25.6% |
| MathArena Final-Answer Competitions | — | 72.9% |
Knowledge Kimi K2.6 leads
GLM-4.7: 47.0 (#80), Kimi K2.6: 54.0 (#54)
| Benchmark | GLM-4.7 | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | 83.3% | 90.8% |
| SimpleQA Verified | 32.2% | 34.9% |
| Vectara Hallucination Rate | 11.7% | 10.8% |
| LMArena Expert | 1424 | 1491 |
Multimodal Not comparable
GLM-4.7: —, Kimi K2.6: 31.6 (#103)
| Benchmark | GLM-4.7 | Kimi K2.6 |
|---|---|---|
| LMArena Vision | — | 1283 |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual Kimi K2.6 leads
GLM-4.7: 52.8 (#79), Kimi K2.6: 54.9 (#37)
| Benchmark | GLM-4.7 | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1417 | 1446 |
| LMArena Chinese | 1495 | 1521 |
| LMArena French | 1432 | 1471 |
| LMArena German | 1424 | 1450 |
| LMArena Japanese | 1439 | 1443 |
| LMArena Korean | 1399 | 1427 |
| LMArena Russian | 1423 | 1446 |
| LMArena Spanish | 1434 | 1464 |
Instruction Following Kimi K2.6 leads
GLM-4.7: 74.4 (#95), Kimi K2.6: 76.3 (#43)
| Benchmark | GLM-4.7 | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1411 | 1451 |
Long Context Kimi K2.6 leads
GLM-4.7: 42.8 (#116), Kimi K2.6: 44.9 (#52)
| Benchmark | GLM-4.7 | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1432 | 1468 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
Writing & Preference Kimi K2.6 leads
GLM-4.7: 60.9 (#93), Kimi K2.6: 68.5 (#26)
| Benchmark | GLM-4.7 | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1435 | 1455 |
| LMArena Creative Writing | 1401 | 1434 |
| EQ-Bench Creative Writing | 1413 | 1725 |
| LMArena Multi-Turn | 1446 | 1453 |
| EQ-Bench 4 | — | 1202 |
Frequently asked questions
Is GLM-4.7 better than Kimi K2.6?
Kimi K2.6 is the stronger model overall, scoring 47.7 to 42.0 on the Noometry Index. GLM-4.7 costs 1.7× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.
Which is cheaper, GLM-4.7 or Kimi K2.6?
GLM-4.7 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Kimi K2.6 lists at $0.95 and $4.
Is GLM-4.7 or Kimi K2.6 better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 44.0 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-4.7 and Kimi K2.6 share?
32 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Kimi K2.6 has 51.