Model comparison
GLM-4.6 vs Kimi K2.5 Instant
Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 41.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. GLM-4.6 scores higher in 2 categories and Kimi K2.5 Instant in 6 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.5 Instant leads 29.7 to 23.7.
Side by side
| GLM-4.6 | Kimi K2.5 Instant | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Moonshot AI |
| Noometry Index | 41.4 | 43.6 |
| Released | 2025-09-30 | — |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 29 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 Instant leads
GLM-4.6: 40.1 (#148), Kimi K2.5 Instant: 42.6 (#97)
| Benchmark | GLM-4.6 | Kimi K2.5 Instant |
|---|---|---|
| LMArena WebDev | 1340 | 1404 |
| LMArena Coding | 1449 | 1484 |
| SWE-bench Verified (bash only) | 55.4% | — |
| SciCode | 38.4% | — |
| ALE-Bench | 340.82 | — |
Agentic & Tool Use Not comparable
GLM-4.6: 32.3 (#66), Kimi K2.5 Instant: —
| Benchmark | GLM-4.6 | Kimi K2.5 Instant |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
Reasoning Kimi K2.5 Instant leads
GLM-4.6: 23.7 (#172), Kimi K2.5 Instant: 29.7 (#90)
| Benchmark | GLM-4.6 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Hard Prompts | 1440 | 1443 |
| Kagi LLM Benchmark | 47.4% | — |
| CritPt | 1.1% | — |
Math Too close to call
GLM-4.6: 39.1 (#111), Kimi K2.5 Instant: 39.4 (#105)
| Benchmark | GLM-4.6 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Math | 1432 | 1442 |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Too close to call
GLM-4.6: 40.2 (#124), Kimi K2.5 Instant: 40.2 (#123)
| Benchmark | GLM-4.6 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Expert | 1431 | 1440 |
| Vectara Hallucination Rate | 9.5% | — |
Multimodal Not comparable
GLM-4.6: —, Kimi K2.5 Instant: 40.2 (#50)
| Benchmark | GLM-4.6 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Vision | — | 1254 |
Multilingual GLM-4.6 leads
GLM-4.6: 53.5 (#66), Kimi K2.5 Instant: 52.0 (#94)
| Benchmark | GLM-4.6 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Non-English | 1426 | 1406 |
| LMArena Chinese | 1499 | 1449 |
| LMArena French | 1459 | 1403 |
| LMArena German | 1447 | 1413 |
| LMArena Korean | 1400 | 1378 |
| LMArena Russian | 1419 | 1404 |
| LMArena Spanish | 1436 | 1447 |
| LMArena Japanese | 1393 | — |
Instruction Following Too close to call
GLM-4.6: 74.3 (#98), Kimi K2.5 Instant: 75.3 (#65)
| Benchmark | GLM-4.6 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Instruction Following | 1410 | 1430 |
Long Context Too close to call
GLM-4.6: 43.4 (#94), Kimi K2.5 Instant: 43.9 (#83)
| Benchmark | GLM-4.6 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Longer Query | 1422 | 1435 |
Writing & Preference Too close to call
GLM-4.6: 61.1 (#90), Kimi K2.5 Instant: 60.6 (#95)
| Benchmark | GLM-4.6 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Text | 1440 | 1420 |
| LMArena Creative Writing | 1411 | 1381 |
| LMArena Multi-Turn | 1427 | 1427 |
| EQ-Bench Creative Writing | 1411 | — |
Frequently asked questions
Is GLM-4.6 better than Kimi K2.5 Instant?
Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 41.4 on the Noometry Index.
Is GLM-4.6 or Kimi K2.5 Instant better for coding?
Kimi K2.5 Instant scores higher on coding benchmarks: 42.6 versus 40.1 in the Noometry coding category.
How many benchmarks do GLM-4.6 and Kimi K2.5 Instant share?
17 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Kimi K2.5 Instant has 18.