Model comparison
GLM-5.2 vs Kimi K2.5
GLM-5.2 is the stronger model overall, scoring 51.1 to 48.1 on the Noometry Index. Kimi K2.5 costs 2.4× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Last verified . 36 shared benchmarks.
Summary
- They share 36 benchmarks with published results for both. GLM-5.2 scores higher in 7 categories and Kimi K2.5 in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.2 leads 42.3 to 31.2.
- The biggest single-benchmark swing is WeirdML: 70.1% for GLM-5.2 and 45.6% for Kimi K2.5.
- Kimi K2.5 is cheaper at $0.45 / $2.25 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 K2.5 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Moonshot AI |
| Noometry Index | 51.1 | 48.1 |
| Released | 2026-06-13 | 2026-01-27 |
| Weights | Open | Open |
| Context window | 1M | 262K |
| Max output | 131K | 262K |
| Input $ / M tokens | $1.40 | $0.45 |
| Output $ / M tokens | $4.40 | $2.25 |
| Results tracked | 51 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.2 leads
GLM-5.2: 51.3 (#41), Kimi K2.5: 48.8 (#53)
| Benchmark | GLM-5.2 | Kimi K2.5 |
|---|---|---|
| SWE-bench Verified | 78.7% | 73.8% |
| LMArena WebDev | 1603 | 1437 |
| SciCode | 50.5% | 49% |
| WeirdML | 70.1% | 45.6% |
| LMArena Coding | 1485 | 1474 |
| ALE-Bench | 1,047 | 821.65 |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| SWE-bench Verified (bash only) | — | 70.8% |
| SWE-bench Multilingual | — | 67.3% |
Agentic & Tool Use Kimi K2.5 leads
GLM-5.2: 32.4 (#63), Kimi K2.5: 34.2 (#48)
| Benchmark | GLM-5.2 | Kimi K2.5 |
|---|---|---|
| Vending-Bench 2 | 8,314 | 1,198 |
| Terminal-Bench | — | 43.2% |
| APEX-Agents | 45.2% | — |
| τ²-bench Banking | 37.1% | — |
| OSWorld | — | 63.3% |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
Reasoning GLM-5.2 leads
GLM-5.2: 42.3 (#52), Kimi K2.5: 31.2 (#80)
| Benchmark | GLM-5.2 | Kimi K2.5 |
|---|---|---|
| ARC-AGI-2 | 22.8% | 11.8% |
| SimpleBench | 58.8% | 46.8% |
| Kagi LLM Benchmark | 62.6% | 78.5% |
| NYT Connections (extended) | 74.3% | 69.9% |
| ARC-AGI-1 | 77% | 65.3% |
| CritPt | 20.9% | 3.1% |
| Chess Puzzles | 21% | 12% |
| LMArena Hard Prompts | 1480 | 1453 |
| Epoch Capabilities Index | 151.78 | 148.03 |
| EnigmaEval | — | 3.4% |
| Thematic Generalization | — | 69.4% |
| EBR-Bench | 9.5% | — |
| Mystery Game Puzzles | 19% | — |
| DTBench | 93.6% | — |
| LMCA | 45.8% | — |
| Surface Evolver Bench | 55.6% | — |
Math GLM-5.2 leads
GLM-5.2: 55.7 (#43), Kimi K2.5: 51.8 (#53)
| Benchmark | GLM-5.2 | Kimi K2.5 |
|---|---|---|
| MathArena Final-Answer Competitions | 67.6% | 62.3% |
| OTIS Mock AIME 2024-2025 | 86.4% | 92.2% |
| LMArena Math | 1482 | 1470 |
| FrontierMath (Tiers 1-3) | 59.2% | — |
| FrontierMath Tier 4 | 29.3% | — |
| ProofBench | 35% | — |
| FrontierMath (Feb 2025 set) | — | 27.9% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#40), Kimi K2.5: 53.6 (#56)
| Benchmark | GLM-5.2 | Kimi K2.5 |
|---|---|---|
| GPQA Diamond | 91.9% | 87.6% |
| SimpleQA Verified | 34.2% | 34.3% |
| LMArena Expert | 1486 | 1466 |
| Humanity's Last Exam | — | 24.4% |
| Vectara Hallucination Rate | — | 14.2% |
Multimodal Not comparable
GLM-5.2: —, Kimi K2.5: 41.1 (#39)
| Benchmark | GLM-5.2 | Kimi K2.5 |
|---|---|---|
| LMArena Vision | — | 1269 |
| LMArena Document | — | 1430 |
Multilingual GLM-5.2 leads
GLM-5.2: 55.8 (#26), Kimi K2.5: 53.9 (#53)
| Benchmark | GLM-5.2 | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1459 | 1433 |
| LMArena Chinese | 1519 | 1495 |
| LMArena French | 1479 | 1454 |
| LMArena German | 1468 | 1441 |
| LMArena Japanese | 1451 | 1421 |
| LMArena Korean | 1445 | 1410 |
| LMArena Russian | 1466 | 1435 |
| LMArena Spanish | 1477 | 1450 |
Instruction Following GLM-5.2 leads
GLM-5.2: 76.9 (#34), Kimi K2.5: 75.3 (#64)
| Benchmark | GLM-5.2 | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1465 | 1431 |
Long Context Kimi K2.5 leads
GLM-5.2: 45.3 (#43), Kimi K2.5: 52.1 (#7)
| Benchmark | GLM-5.2 | Kimi K2.5 |
|---|---|---|
| LMArena Longer Query | 1479 | 1445 |
| Fiction.LiveBench | — | 86.1% |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.4 (#21), Kimi K2.5: 65.1 (#53)
| Benchmark | GLM-5.2 | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1470 | 1445 |
| LMArena Creative Writing | 1462 | 1423 |
| EQ-Bench Creative Writing | 1757 | 1579 |
| LMArena Multi-Turn | 1469 | 1444 |
| EQ-Bench 4 | 1222 | — |
Frequently asked questions
Is GLM-5.2 better than Kimi K2.5?
GLM-5.2 is the stronger model overall, scoring 51.1 to 48.1 on the Noometry Index. Kimi K2.5 costs 2.4× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Which is cheaper, GLM-5.2 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-5.2 lists at $1.40 and $4.40.
Is GLM-5.2 or Kimi K2.5 better for coding?
GLM-5.2 scores higher on coding benchmarks: 51.3 versus 48.8 in the Noometry coding category.
Which has the bigger context window?
GLM-5.2 does, with 1M tokens against 262K.
How many benchmarks do GLM-5.2 and Kimi K2.5 share?
36 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and Kimi K2.5 has 51.