Model comparison
GLM-4.5-Air vs Kimi K2.5
Kimi K2.5 is the stronger model overall, scoring 48.1 to 38.9 on the Noometry Index. GLM-4.5-Air costs 2.1× less per token, which makes it the better buy when Kimi K2.5's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. GLM-4.5-Air scores higher in 0 categories and Kimi K2.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.5 leads 53.6 to 35.0.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 43% for GLM-4.5-Air and 78.5% for Kimi K2.5.
- GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $0.45 / $2.25 for Kimi K2.5.
- Kimi K2.5 accepts more context: 262K tokens versus 131K.
Side by side
| GLM-4.5-Air | Kimi K2.5 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Moonshot AI |
| Noometry Index | 38.9 | 48.1 |
| Released | 2025-07-20 | 2026-01-27 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 98K | 262K |
| Input $ / M tokens | $0.20 | $0.45 |
| Output $ / M tokens | $1.10 | $2.25 |
| Results tracked | 27 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
GLM-4.5-Air: 33.3 (#259), Kimi K2.5: 48.8 (#53)
| Benchmark | GLM-4.5-Air | Kimi K2.5 |
|---|---|---|
| LMArena Coding | 1397 | 1474 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 70.8% |
| LMArena WebDev | — | 1437 |
| SWE-bench Multilingual | — | 67.3% |
| SciCode | — | 49% |
| GSO | 2.9% | — |
| WeirdML | — | 45.6% |
| ALE-Bench | — | 821.65 |
Agentic & Tool Use Not comparable
GLM-4.5-Air: —, Kimi K2.5: 34.2 (#48)
| Benchmark | GLM-4.5-Air | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | — | 43.2% |
| OSWorld | — | 63.3% |
| Vending-Bench 2 | — | 1,198 |
Reasoning Kimi K2.5 leads
GLM-4.5-Air: 24.1 (#166), Kimi K2.5: 31.2 (#80)
| Benchmark | GLM-4.5-Air | Kimi K2.5 |
|---|---|---|
| Kagi LLM Benchmark | 43% | 78.5% |
| LMArena Hard Prompts | 1379 | 1453 |
| ARC-AGI-2 | — | 11.8% |
| SimpleBench | — | 46.8% |
| NYT Connections (extended) | — | 69.9% |
| ARC-AGI-1 | — | 65.3% |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| EnigmaEval | — | 3.4% |
| Thematic Generalization | — | 69.4% |
| Epoch Capabilities Index | — | 148.03 |
| ForecastBench | 59.2 | — |
Math Kimi K2.5 leads
GLM-4.5-Air: 36.2 (#170), Kimi K2.5: 51.8 (#53)
| Benchmark | GLM-4.5-Air | Kimi K2.5 |
|---|---|---|
| LMArena Math | 1396 | 1470 |
| MathArena Final-Answer Competitions | — | 62.3% |
| OTIS Mock AIME 2024-2025 | — | 92.2% |
| Omni-MATH | 39.1% | — |
| FrontierMath (Feb 2025 set) | — | 27.9% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Kimi K2.5 leads
GLM-4.5-Air: 35.0 (#191), Kimi K2.5: 53.6 (#56)
| Benchmark | GLM-4.5-Air | Kimi K2.5 |
|---|---|---|
| Humanity's Last Exam | 8.1% | 24.4% |
| Vectara Hallucination Rate | 9.3% | 14.2% |
| LMArena Expert | 1370 | 1466 |
| GPQA Diamond | — | 87.6% |
| SimpleQA Verified | — | 34.3% |
| MMLU-Pro | 76.2% | — |
| GPQA (HELM) | 59.4% | — |
Multimodal Not comparable
GLM-4.5-Air: —, Kimi K2.5: 41.1 (#39)
| Benchmark | GLM-4.5-Air | Kimi K2.5 |
|---|---|---|
| LMArena Vision | — | 1269 |
| LMArena Document | — | 1430 |
Multilingual Kimi K2.5 leads
GLM-4.5-Air: 49.1 (#135), Kimi K2.5: 53.9 (#53)
| Benchmark | GLM-4.5-Air | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1366 | 1433 |
| LMArena Chinese | 1426 | 1495 |
| LMArena French | 1399 | 1454 |
| LMArena German | 1377 | 1441 |
| LMArena Japanese | 1348 | 1421 |
| LMArena Korean | 1308 | 1410 |
| LMArena Russian | 1373 | 1435 |
| LMArena Spanish | 1386 | 1450 |
Instruction Following Kimi K2.5 leads
GLM-4.5-Air: 69.6 (#171), Kimi K2.5: 75.3 (#64)
| Benchmark | GLM-4.5-Air | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1354 | 1431 |
| IFEval | 81.2% | — |
Long Context Kimi K2.5 leads
GLM-4.5-Air: 41.6 (#135), Kimi K2.5: 52.1 (#7)
| Benchmark | GLM-4.5-Air | Kimi K2.5 |
|---|---|---|
| LMArena Longer Query | 1366 | 1445 |
| Fiction.LiveBench | — | 86.1% |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |
Writing & Preference Kimi K2.5 leads
GLM-4.5-Air: 55.9 (#139), Kimi K2.5: 65.1 (#53)
| Benchmark | GLM-4.5-Air | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1384 | 1445 |
| LMArena Creative Writing | 1343 | 1423 |
| LMArena Multi-Turn | 1371 | 1444 |
| EQ-Bench Creative Writing | — | 1579 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than Kimi K2.5?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 38.9 on the Noometry Index. GLM-4.5-Air costs 2.1× less per token, which makes it the better buy when Kimi K2.5's lead doesn't matter for your workload.
Which is cheaper, GLM-4.5-Air or Kimi K2.5?
GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; Kimi K2.5 lists at $0.45 and $2.25.
Is GLM-4.5-Air or Kimi K2.5 better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 33.3 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.5 does, with 262K tokens against 131K.
How many benchmarks do GLM-4.5-Air and Kimi K2.5 share?
20 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Kimi K2.5 has 51.