# GLM-5.1 vs Kimi K2 (Jul 2025)

> GLM-5.1 is the stronger model overall, scoring 47.8 to 41.2 on the Noometry Index. Kimi K2 (Jul 2025) costs 2.1× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-kimi-k2
- Last updated: 2026-10-12
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and Kimi K2 (Jul 2025) in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.1 leads 54.9 to 37.3.
- The biggest single-benchmark swing is SimpleBench: 55.1% for GLM-5.1 and 26.3% for Kimi K2 (Jul 2025).
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- Kimi K2 (Jul 2025) accepts more context: 262K tokens versus 200K.

## Snapshot

| | GLM-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| Provider | Z.ai (Zhipu) | Moonshot AI |
| Noometry Index | 47.8 | 41.2 |
| Rank | 59 | 140 |
| Context | 200K | 262K |
| Input $/M | $1.40 | $0.57 |
| Output $/M | $4.40 | $2.30 |
| Weights | Open | Open |

## Coding

- GLM-5.1: 48.7 (#55)
- Kimi K2 (Jul 2025): 42.4 (#102)

| Benchmark | GLM-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| WeirdML | 57.1% | 42.8% |
| LMArena Coding | 1485 | 1399 |
| ALE-Bench | 887.1 | 597.5 |
| SWE-bench Verified | 74.2% | — |
| SWE-bench Verified (bash only) | — | 63.4% |
| Aider Polyglot | — | 59.1% |
| LMArena WebDev | 1508 | — |
| SciCode | 43.8% | — |
| GSO | — | 4.9% |

## Agentic & Tool Use

- GLM-5.1: 24.9 (#113)
- Kimi K2 (Jul 2025): 32.4 (#64)

| Benchmark | GLM-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | — | 35.7% |
| APEX-Agents | 40.9% | — |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| METR Time Horizons | — | 59.2% |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 39.1 (#60)
- Kimi K2 (Jul 2025): 23.3 (#179)

| Benchmark | GLM-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| SimpleBench | 55.1% | 26.3% |
| LMArena Hard Prompts | 1472 | 1384 |
| Epoch Capabilities Index | 149.84 | 146.01 |
| Kagi LLM Benchmark | — | 64.4% |
| NYT Connections (extended) | 77.7% | — |
| CritPt | 4.6% | — |
| Chess Puzzles | 19% | — |
| Thematic Generalization | 69.8% | — |
| ForecastBench | — | 60.2 |

## Math

- GLM-5.1: 49.7 (#60)
- Kimi K2 (Jul 2025): 42.7 (#83)

| Benchmark | GLM-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Math | 1473 | 1397 |
| FrontierMath (Feb 2025 set) | 33.4% | 21.4% |
| FrontierMath Tier 4 (v1) | 12.5% | 0% |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| ProofBench | 22.2% | — |
| Omni-MATH | — | 65.4% |

## Knowledge

- GLM-5.1: 54.9 (#50)
- Kimi K2 (Jul 2025): 37.3 (#157)

| Benchmark | GLM-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Expert | 1476 | 1365 |
| GPQA Diamond | 89.9% | — |
| SimpleQA Verified | 34% | — |
| MMLU-Pro | — | 81.9% |
| Confabulations | — | 20.4% |
| Vectara Hallucination Rate | — | 17.9% |
| GPQA (HELM) | — | 65.3% |

## Multilingual

- GLM-5.1: 55.0 (#36)
- Kimi K2 (Jul 2025): 49.6 (#130)

| Benchmark | GLM-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1447 | 1372 |
| LMArena Chinese | 1515 | 1415 |
| LMArena French | 1474 | 1379 |
| LMArena German | 1465 | 1387 |
| LMArena Japanese | 1434 | 1349 |
| LMArena Korean | 1418 | 1325 |
| LMArena Russian | 1454 | 1385 |
| LMArena Spanish | 1469 | 1386 |

## Instruction Following

- GLM-5.1: 76.3 (#42)
- Kimi K2 (Jul 2025): 71.1 (#156)

| Benchmark | GLM-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Instruction Following | 1451 | 1348 |
| IFEval | — | 85% |

## Long Context

- GLM-5.1: 44.9 (#53)
- Kimi K2 (Jul 2025): 41.2 (#145)

| Benchmark | GLM-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Longer Query | 1466 | 1353 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 17.6% |

## Writing & Preference

- GLM-5.1: 66.9 (#31)
- Kimi K2 (Jul 2025): 62.3 (#78)

| Benchmark | GLM-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1461 | 1380 |
| LMArena Creative Writing | 1453 | 1350 |
| EQ-Bench Creative Writing | 1592 | 1666 |
| LMArena Multi-Turn | 1472 | 1371 |
| Short-Story Creative Writing | — | 85.6% |
| WildBench | — | 86.2% |

## FAQ

### Is GLM-5.1 better than Kimi K2 (Jul 2025)?

GLM-5.1 is the stronger model overall, scoring 47.8 to 41.2 on the Noometry Index. Kimi K2 (Jul 2025) costs 2.1× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.

### Which is cheaper, GLM-5.1 or Kimi K2 (Jul 2025)?

Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.

### Is GLM-5.1 or Kimi K2 (Jul 2025) better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.7 versus 42.4 in the Noometry coding category.

### Which has the bigger context window?

Kimi K2 (Jul 2025) does, with 262K tokens against 200K.

### How many benchmarks do GLM-5.1 and Kimi K2 (Jul 2025) share?

24 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Kimi K2 (Jul 2025) has 42.