Model comparison
GLM-4.5V vs Kimi K2 (Jul 2025)
Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 39.2 on the Noometry Index.
Last verified . 14 shared benchmarks.
Summary
- They share 14 benchmarks with published results for both. GLM-4.5V scores higher in 1 category and Kimi K2 (Jul 2025) in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2 (Jul 2025) leads 62.5 to 52.7.
- GLM-4.5V is cheaper at $0.60 / $1.80 per million input/output tokens, against $0.57 / $2.30 for Kimi K2 (Jul 2025).
- Kimi K2 (Jul 2025) accepts more context: 262K tokens versus 64K.
Side by side
| GLM-4.5V | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Moonshot AI |
| Noometry Index | 39.2 | 40.9 |
| Released | 2025-08-11 | 2025-07-12 |
| Weights | Open | Open |
| Context window | 64K | 262K |
| Max output | 16K | 262K |
| Input $ / M tokens | $0.60 | $0.57 |
| Output $ / M tokens | $1.80 | $2.30 |
| Results tracked | 15 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 (Jul 2025) leads
GLM-4.5V: 38.9 (#152), Kimi K2 (Jul 2025): 43.1 (#83)
| Benchmark | GLM-4.5V | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Coding | 1347 | 1399 |
| SWE-bench Verified (bash only) | — | 63.4% |
| Aider Polyglot | — | 59.1% |
| GSO | — | 4.9% |
| WeirdML | — | 42.8% |
| ALE-Bench | — | 597.5 |
Agentic & Tool Use Not comparable
GLM-4.5V: —, Kimi K2 (Jul 2025): 32.2 (#59)
| Benchmark | GLM-4.5V | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | — | 35.7% |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| METR Time Horizons | — | 59.2% |
Reasoning GLM-4.5V leads
GLM-4.5V: 26.5 (#118), Kimi K2 (Jul 2025): 22.7 (#173)
| Benchmark | GLM-4.5V | Kimi K2 (Jul 2025) |
|---|---|---|
| Kagi LLM Benchmark | 59.8% | 64.4% |
| LMArena Hard Prompts | 1335 | 1384 |
| SimpleBench | — | 26.3% |
| Epoch Capabilities Index | — | 146.02 |
| ForecastBench | — | 60.2 |
Math Kimi K2 (Jul 2025) leads
GLM-4.5V: 34.7 (#157), Kimi K2 (Jul 2025): 40.1 (#81)
| Benchmark | GLM-4.5V | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Math | 1353 | 1396 |
| Omni-MATH | — | 65.4% |
| FrontierMath (Feb 2025 set) | — | 21.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Too close to call
GLM-4.5V: 36.8 (#155), Kimi K2 (Jul 2025): 36.9 (#153)
| Benchmark | GLM-4.5V | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Expert | 1353 | 1363 |
| MMLU-Pro | — | 81.9% |
| Confabulations | — | 20.4% |
| Vectara Hallucination Rate | — | 17.9% |
| GPQA (HELM) | — | 65.3% |
Multimodal Not comparable
GLM-4.5V: 33.6 (#86), Kimi K2 (Jul 2025): —
| Benchmark | GLM-4.5V | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Vision | 1154 | — |
Multilingual Kimi K2 (Jul 2025) leads
GLM-4.5V: 44.9 (#172), Kimi K2 (Jul 2025): 49.8 (#125)
| Benchmark | GLM-4.5V | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1304 | 1372 |
| LMArena Chinese | 1338 | 1416 |
| LMArena Russian | 1299 | 1384 |
| LMArena Spanish | 1335 | 1383 |
| LMArena French | — | 1379 |
| LMArena German | — | 1386 |
| LMArena Japanese | — | 1349 |
| LMArena Korean | — | 1324 |
Instruction Following Kimi K2 (Jul 2025) leads
GLM-4.5V: 69.4 (#170), Kimi K2 (Jul 2025): 71.3 (#151)
| Benchmark | GLM-4.5V | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Instruction Following | 1311 | 1347 |
| IFEval | — | 85% |
Long Context Kimi K2 (Jul 2025) leads
GLM-4.5V: 39.6 (#166), Kimi K2 (Jul 2025): 41.2 (#140)
| Benchmark | GLM-4.5V | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Longer Query | 1305 | 1353 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 17.6% |
Writing & Preference Kimi K2 (Jul 2025) leads
GLM-4.5V: 52.7 (#162), Kimi K2 (Jul 2025): 62.5 (#76)
| Benchmark | GLM-4.5V | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1333 | 1380 |
| LMArena Creative Writing | 1295 | 1349 |
| LMArena Multi-Turn | 1333 | 1371 |
| Short-Story Creative Writing | — | 85.6% |
| EQ-Bench Creative Writing | — | 1666 |
| WildBench | — | 86.2% |
Frequently asked questions
Is GLM-4.5V better than Kimi K2 (Jul 2025)?
Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 39.2 on the Noometry Index.
Which is cheaper, GLM-4.5V or Kimi K2 (Jul 2025)?
GLM-4.5V is cheaper. It lists at $0.60 per million input tokens and $1.80 per million output tokens; Kimi K2 (Jul 2025) lists at $0.57 and $2.30.
Is GLM-4.5V or Kimi K2 (Jul 2025) better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 43.1 versus 38.9 in the Noometry coding category.
Which has the bigger context window?
Kimi K2 (Jul 2025) does, with 262K tokens against 64K.
How many benchmarks do GLM-4.5V and Kimi K2 (Jul 2025) share?
14 benchmarks have published results for both models. GLM-4.5V has 15 scored results on Noometry and Kimi K2 (Jul 2025) has 42.