Model comparison
GLM-4.6 vs Kimi K2.5
Kimi K2.5 is the stronger model overall, scoring 47.8 to 40.9 on the Noometry Index.
Last verified . 28 shared benchmarks.
Summary
- They share 28 benchmarks with published results for both. GLM-4.6 scores higher in 0 categories and Kimi K2.5 in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.5 leads 53.6 to 39.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 47.4% for GLM-4.6 and 78.5% for Kimi K2.5.
- Kimi K2.5 is cheaper at $0.45 / $2.25 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- Kimi K2.5 accepts more context: 262K tokens versus 205K.
Side by side
| GLM-4.6 | Kimi K2.5 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Moonshot AI |
| Noometry Index | 40.9 | 47.8 |
| Released | 2025-09-30 | 2026-01-27 |
| Weights | Open | Open |
| Context window | 205K | 262K |
| Max output | 131K | 262K |
| Input $ / M tokens | $0.60 | $0.45 |
| Output $ / M tokens | $2.20 | $2.25 |
| Results tracked | 29 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
GLM-4.6: 39.9 (#137), Kimi K2.5: 48.7 (#48)
| Benchmark | GLM-4.6 | Kimi K2.5 |
|---|---|---|
| SWE-bench Verified (bash only) | 55.4% | 70.8% |
| LMArena WebDev | 1339 | 1436 |
| SciCode | 38.4% | 49% |
| LMArena Coding | 1449 | 1474 |
| ALE-Bench | 340.82 | 821.65 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Multilingual | — | 67.3% |
| WeirdML | — | 45.6% |
Agentic & Tool Use Kimi K2.5 leads
GLM-4.6: 32.1 (#60), Kimi K2.5: 34.0 (#44)
| Benchmark | GLM-4.6 | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | 24.5% | 43.2% |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| OSWorld | — | 63.3% |
| Vending-Bench 2 | — | 1,198 |
Reasoning Kimi K2.5 leads
GLM-4.6: 23.1 (#168), Kimi K2.5: 31.2 (#74)
| Benchmark | GLM-4.6 | Kimi K2.5 |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | 78.5% |
| CritPt | 1.1% | 3.1% |
| LMArena Hard Prompts | 1440 | 1454 |
| ARC-AGI-2 | — | 11.8% |
| SimpleBench | — | 46.8% |
| NYT Connections (extended) | — | 69.9% |
| ARC-AGI-1 | — | 65.3% |
| Chess Puzzles | — | 12% |
| EnigmaEval | — | 3.4% |
| Thematic Generalization | — | 69.4% |
| Epoch Capabilities Index | — | 148.05 |
Math Kimi K2.5 leads
GLM-4.6: 36.4 (#115), Kimi K2.5: 50.3 (#46)
| Benchmark | GLM-4.6 | Kimi K2.5 |
|---|---|---|
| LMArena Math | 1431 | 1470 |
| FrontierMath (Feb 2025 set) | 3.8% | 27.9% |
| FrontierMath Tier 4 (v1) | 2.1% | 4.2% |
| MathArena Final-Answer Competitions | — | 62.3% |
| OTIS Mock AIME 2024-2025 | — | 92.2% |
Knowledge Kimi K2.5 leads
GLM-4.6: 39.6 (#118), Kimi K2.5: 53.6 (#52)
| Benchmark | GLM-4.6 | Kimi K2.5 |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 14.2% |
| LMArena Expert | 1432 | 1466 |
| GPQA Diamond | — | 87.6% |
| Humanity's Last Exam | — | 24.4% |
| SimpleQA Verified | — | 34.3% |
Multimodal Not comparable
GLM-4.6: —, Kimi K2.5: 40.4 (#37)
| Benchmark | GLM-4.6 | Kimi K2.5 |
|---|---|---|
| LMArena Vision | — | 1269 |
| LMArena Document | — | 1430 |
Multilingual Too close to call
GLM-4.6: 53.6 (#62), Kimi K2.5: 54.1 (#50)
| Benchmark | GLM-4.6 | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1426 | 1433 |
| LMArena Chinese | 1500 | 1495 |
| LMArena French | 1459 | 1454 |
| LMArena German | 1447 | 1441 |
| LMArena Japanese | 1394 | 1422 |
| LMArena Korean | 1401 | 1412 |
| LMArena Russian | 1418 | 1436 |
| LMArena Spanish | 1436 | 1450 |
Instruction Following Kimi K2.5 leads
GLM-4.6: 74.5 (#93), Kimi K2.5: 75.5 (#60)
| Benchmark | GLM-4.6 | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1410 | 1431 |
Long Context Kimi K2.5 leads
GLM-4.6: 43.4 (#91), Kimi K2.5: 52.1 (#7)
| Benchmark | GLM-4.6 | Kimi K2.5 |
|---|---|---|
| LMArena Longer Query | 1423 | 1445 |
| Fiction.LiveBench | — | 86.1% |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |
Writing & Preference Kimi K2.5 leads
GLM-4.6: 61.3 (#86), Kimi K2.5: 65.3 (#51)
| Benchmark | GLM-4.6 | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1440 | 1445 |
| LMArena Creative Writing | 1411 | 1423 |
| EQ-Bench Creative Writing | 1411 | 1579 |
| LMArena Multi-Turn | 1427 | 1444 |
Frequently asked questions
Is GLM-4.6 better than Kimi K2.5?
Kimi K2.5 is the stronger model overall, scoring 47.8 to 40.9 on the Noometry Index.
Which is cheaper, GLM-4.6 or Kimi K2.5?
Kimi K2.5 is cheaper. It lists at $0.45 per million input tokens and $2.25 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.
Is GLM-4.6 or Kimi K2.5 better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.7 versus 39.9 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.5 does, with 262K tokens against 205K.
How many benchmarks do GLM-4.6 and Kimi K2.5 share?
28 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Kimi K2.5 has 51.