# GLM-4.5 vs Kimi K2 (Jul 2025)

> GLM-4.5 and Kimi K2 (Jul 2025) score almost the same on the Noometry Index (42.0 vs 41.2), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/glm-4-5-vs-kimi-k2
- Last updated: 2026-10-11
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. GLM-4.5 scores higher in 3 categories and Kimi K2 (Jul 2025) in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-4.5 leads 28.6 to 23.3.
- The biggest single-benchmark swing is Short-Story Creative Writing: 73.4% for GLM-4.5 and 85.6% for Kimi K2 (Jul 2025).
- Both cost about the same: $0.60 input and $2.20 output per million tokens.
- Kimi K2 (Jul 2025) accepts more context: 262K tokens versus 131K.

## Snapshot

| | GLM-4.5 | Kimi K2 (Jul 2025) |
|---|---|---|
| Provider | Z.ai (Zhipu) | Moonshot AI |
| Noometry Index | 42.0 | 41.2 |
| Rank | 122 | 140 |
| Context | 131K | 262K |
| Input $/M | $0.60 | $0.57 |
| Output $/M | $2.20 | $2.30 |
| Weights | Open | Open |

## Coding

- GLM-4.5: 41.4 (#125)
- Kimi K2 (Jul 2025): 42.4 (#102)

| Benchmark | GLM-4.5 | Kimi K2 (Jul 2025) |
|---|---|---|
| SWE-bench Verified (bash only) | 54.2% | 63.4% |
| WeirdML | 40.6% | 42.8% |
| LMArena Coding | 1434 | 1399 |
| ALE-Bench | 344.82 | 597.5 |
| Aider Polyglot | — | 59.1% |
| GSO | — | 4.9% |
| AlgoTune | 1.52 | — |

## Agentic & Tool Use

- GLM-4.5: —
- Kimi K2 (Jul 2025): 32.4 (#64)

| Benchmark | GLM-4.5 | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | — | 35.7% |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| METR Time Horizons | — | 59.2% |

## Reasoning

- GLM-4.5: 28.6 (#100)
- Kimi K2 (Jul 2025): 23.3 (#179)

| Benchmark | GLM-4.5 | Kimi K2 (Jul 2025) |
|---|---|---|
| Kagi LLM Benchmark | 57.9% | 64.4% |
| LMArena Hard Prompts | 1429 | 1384 |
| SimpleBench | — | 26.3% |
| Epoch Capabilities Index | — | 146.01 |
| ForecastBench | — | 60.2 |

## Math

- GLM-4.5: 39.0 (#116)
- Kimi K2 (Jul 2025): 42.7 (#83)

| Benchmark | GLM-4.5 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Math | 1427 | 1397 |
| Omni-MATH | — | 65.4% |
| FrontierMath (Feb 2025 set) | — | 21.4% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- GLM-4.5: 35.9 (#179)
- Kimi K2 (Jul 2025): 37.3 (#157)

| Benchmark | GLM-4.5 | Kimi K2 (Jul 2025) |
|---|---|---|
| Confabulations | 11.3% | 20.4% |
| LMArena Expert | 1433 | 1365 |
| Humanity's Last Exam | 8.3% | — |
| MMLU-Pro | — | 81.9% |
| Vectara Hallucination Rate | — | 17.9% |
| GPQA (HELM) | — | 65.3% |

## Multilingual

- GLM-4.5: 52.8 (#77)
- Kimi K2 (Jul 2025): 49.6 (#130)

| Benchmark | GLM-4.5 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1417 | 1372 |
| LMArena Chinese | 1465 | 1415 |
| LMArena French | 1418 | 1379 |
| LMArena German | 1407 | 1387 |
| LMArena Japanese | 1415 | 1349 |
| LMArena Korean | 1380 | 1325 |
| LMArena Russian | 1414 | 1385 |
| LMArena Spanish | 1454 | 1386 |

## Instruction Following

- GLM-4.5: 74.1 (#104)
- Kimi K2 (Jul 2025): 71.1 (#156)

| Benchmark | GLM-4.5 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Instruction Following | 1404 | 1348 |
| IFEval | — | 85% |

## Long Context

- GLM-4.5: 38.2 (#201)
- Kimi K2 (Jul 2025): 41.2 (#145)

| Benchmark | GLM-4.5 | Kimi K2 (Jul 2025) |
|---|---|---|
| Fiction.LiveBench | 58.3% | 66.7% |
| LMArena Longer Query | 1412 | 1353 |
| CL-bench | — | 17.6% |

## Writing & Preference

- GLM-4.5: 57.5 (#127)
- Kimi K2 (Jul 2025): 62.3 (#78)

| Benchmark | GLM-4.5 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1430 | 1380 |
| LMArena Creative Writing | 1395 | 1350 |
| Short-Story Creative Writing | 73.4% | 85.6% |
| EQ-Bench Creative Writing | 1343 | 1666 |
| LMArena Multi-Turn | 1415 | 1371 |
| WildBench | — | 86.2% |

## FAQ

### Is GLM-4.5 better than Kimi K2 (Jul 2025)?

GLM-4.5 and Kimi K2 (Jul 2025) score almost the same on the Noometry Index (42.0 vs 41.2), so choose on price, context window or the category you care about most.

### Which is cheaper, GLM-4.5 or Kimi K2 (Jul 2025)?

GLM-4.5 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Kimi K2 (Jul 2025) lists at $0.57 and $2.30.

### Is GLM-4.5 or Kimi K2 (Jul 2025) better for coding?

Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 41.4 in the Noometry coding category.

### Which has the bigger context window?

Kimi K2 (Jul 2025) does, with 262K tokens against 131K.

### How many benchmarks do GLM-4.5 and Kimi K2 (Jul 2025) share?

25 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Kimi K2 (Jul 2025) has 42.