Model comparison
GLM-5V-Turbo vs Kimi K2 (Jul 2025)
GLM-5V-Turbo is the stronger model overall, scoring 43.8 to 41.2 on the Noometry Index. Kimi K2 (Jul 2025) costs 1.9× less per token, which makes it the better buy when GLM-5V-Turbo's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Summary
- They share 16 benchmarks with published results for both. GLM-5V-Turbo scores higher in 6 categories and Kimi K2 (Jul 2025) in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5V-Turbo leads 29.7 to 23.3.
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $1.20 / $4 for GLM-5V-Turbo.
- Kimi K2 (Jul 2025) accepts more context: 262K tokens versus 200K.
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.
Side by side
| GLM-5V-Turbo | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Moonshot AI |
| Noometry Index | 43.8 | 41.2 |
| Released | 2026-04-01 | 2025-07-12 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 131K | 262K |
| Input $ / M tokens | $1.20 | $0.57 |
| Output $ / M tokens | $4 | $2.30 |
| Results tracked | 19 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-5V-Turbo: 42.1 (#111), Kimi K2 (Jul 2025): 42.4 (#102)
| Benchmark | GLM-5V-Turbo | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Coding | 1466 | 1399 |
| SWE-bench Verified (bash only) | — | 63.4% |
| Aider Polyglot | — | 59.1% |
| LMArena WebDev | 1401 | — |
| GSO | — | 4.9% |
| WeirdML | — | 42.8% |
| ALE-Bench | — | 597.5 |
Agentic & Tool Use Not comparable
GLM-5V-Turbo: —, Kimi K2 (Jul 2025): 32.4 (#64)
| Benchmark | GLM-5V-Turbo | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | — | 35.7% |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| METR Time Horizons | — | 59.2% |
Reasoning GLM-5V-Turbo leads
GLM-5V-Turbo: 29.7 (#89), Kimi K2 (Jul 2025): 23.3 (#179)
| Benchmark | GLM-5V-Turbo | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1384 |
| SimpleBench | — | 26.3% |
| Kagi LLM Benchmark | — | 64.4% |
| Epoch Capabilities Index | — | 146.01 |
| ForecastBench | — | 60.2 |
Math Kimi K2 (Jul 2025) leads
GLM-5V-Turbo: 39.4 (#106), Kimi K2 (Jul 2025): 42.7 (#83)
| Benchmark | GLM-5V-Turbo | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Math | 1441 | 1397 |
| Omni-MATH | — | 65.4% |
| FrontierMath (Feb 2025 set) | — | 21.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge GLM-5V-Turbo leads
GLM-5V-Turbo: 40.6 (#117), Kimi K2 (Jul 2025): 37.3 (#157)
| Benchmark | GLM-5V-Turbo | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Expert | 1452 | 1365 |
| MMLU-Pro | — | 81.9% |
| Confabulations | — | 20.4% |
| Vectara Hallucination Rate | — | 17.9% |
| GPQA (HELM) | — | 65.3% |
Multimodal Not comparable
GLM-5V-Turbo: 40.9 (#42), Kimi K2 (Jul 2025): —
| Benchmark | GLM-5V-Turbo | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Vision | 1264 | — |
| LMArena Document | 1416 | — |
Multilingual GLM-5V-Turbo leads
GLM-5V-Turbo: 53.0 (#73), Kimi K2 (Jul 2025): 49.6 (#130)
| Benchmark | GLM-5V-Turbo | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1420 | 1372 |
| LMArena Chinese | 1488 | 1415 |
| LMArena French | 1444 | 1379 |
| LMArena German | 1423 | 1387 |
| LMArena Korean | 1396 | 1325 |
| LMArena Russian | 1431 | 1385 |
| LMArena Spanish | 1450 | 1386 |
| LMArena Japanese | — | 1349 |
Instruction Following GLM-5V-Turbo leads
GLM-5V-Turbo: 75.0 (#80), Kimi K2 (Jul 2025): 71.1 (#156)
| Benchmark | GLM-5V-Turbo | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Instruction Following | 1423 | 1348 |
| IFEval | — | 85% |
Long Context GLM-5V-Turbo leads
GLM-5V-Turbo: 44.0 (#80), Kimi K2 (Jul 2025): 41.2 (#145)
| Benchmark | GLM-5V-Turbo | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Longer Query | 1438 | 1353 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 17.6% |
Writing & Preference Too close to call
GLM-5V-Turbo: 62.5 (#73), Kimi K2 (Jul 2025): 62.3 (#78)
| Benchmark | GLM-5V-Turbo | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1437 | 1380 |
| LMArena Creative Writing | 1416 | 1350 |
| LMArena Multi-Turn | 1432 | 1371 |
| Short-Story Creative Writing | — | 85.6% |
| EQ-Bench Creative Writing | — | 1666 |
| WildBench | — | 86.2% |
Frequently asked questions
Is GLM-5V-Turbo better than Kimi K2 (Jul 2025)?
GLM-5V-Turbo is the stronger model overall, scoring 43.8 to 41.2 on the Noometry Index. Kimi K2 (Jul 2025) costs 1.9× less per token, which makes it the better buy when GLM-5V-Turbo's lead doesn't matter for your workload.
Which is cheaper, GLM-5V-Turbo 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-5V-Turbo lists at $1.20 and $4.
Is GLM-5V-Turbo or Kimi K2 (Jul 2025) better for coding?
They score almost the same on coding (42.1 vs 42.4); test both on your own repository before choosing.
Which has the bigger context window?
Kimi K2 (Jul 2025) does, with 262K tokens against 200K.
How many benchmarks do GLM-5V-Turbo and Kimi K2 (Jul 2025) share?
16 benchmarks have published results for both models. GLM-5V-Turbo has 19 scored results on Noometry and Kimi K2 (Jul 2025) has 42.