Model comparison
GLM-4.5 vs Kimi K3
Kimi K3 is the stronger model overall, scoring 59.5 to 41.4 on the Noometry Index. GLM-4.5 costs 6.0× less per token, which makes it the better buy when Kimi K3'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 scores higher in 0 categories and Kimi K3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K3 leads 74.0 to 36.3.
- The biggest single-benchmark swing is WeirdML: 40.6% for GLM-4.5 and 82.6% for Kimi K3.
- GLM-4.5 is cheaper at $0.60 / $2.20 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 131K.
Side by side
| GLM-4.5 | Kimi K3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Moonshot AI |
| Noometry Index | 41.4 | 59.5 |
| Released | 2025-07-27 | 2026-07-16 |
| Weights | Open | Open |
| Context window | 131K | 1.05M |
| Max output | 98K | 1.05M |
| Input $ / M tokens | $0.60 | $3 |
| Output $ / M tokens | $2.20 | $15 |
| Results tracked | 27 | 53 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
GLM-4.5: 41.1 (#121), Kimi K3: 60.6 (#8)
| Benchmark | GLM-4.5 | Kimi K3 |
|---|---|---|
| WeirdML | 40.6% | 82.6% |
| LMArena Coding | 1434 | 1509 |
| ALE-Bench | 344.82 | 1,524 |
| DeepSWE | — | 68.5% |
| FrontierCode | — | 44.2% |
| SWE-bench Verified (bash only) | 54.2% | — |
| LMArena WebDev | — | 1659 |
| FrontierSWE | — | 25.9% |
| SciCode | — | 59.5% |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Not comparable
GLM-4.5: —, Kimi K3: 41.8 (#19)
| Benchmark | GLM-4.5 | Kimi K3 |
|---|---|---|
| APEX-Agents | — | 50.6% |
| τ²-bench Banking | — | 37.1% |
| PostTrainBench | — | 32% |
| GBAEval | — | 48.3% |
| GDP.pdf | — | 19% |
| Vending-Bench 2 | — | 5,165 |
Reasoning Kimi K3 leads
GLM-4.5: 27.7 (#99), Kimi K3: 63.0 (#15)
| Benchmark | GLM-4.5 | Kimi K3 |
|---|---|---|
| LMArena Hard Prompts | 1430 | 1495 |
| ARC-AGI-2 | — | 60.4% |
| SimpleBench | — | 60.7% |
| Kagi LLM Benchmark | 57.9% | — |
| NYT Connections (extended) | — | 93.6% |
| ARC-AGI-1 | — | 94.5% |
| CritPt | — | 23.4% |
| Chess Puzzles | — | 39% |
| Mystery Game Puzzles | — | 26% |
| DTBench | — | 91.2% |
| LMCA | — | 52.7% |
| Surface Evolver Bench | — | 95% |
| Epoch Capabilities Index | — | 157.68 |
| ForecastBench | — | 61.1 |
Math Kimi K3 leads
GLM-4.5: 36.3 (#119), Kimi K3: 74.0 (#13)
| Benchmark | GLM-4.5 | Kimi K3 |
|---|---|---|
| LMArena Math | 1427 | 1493 |
| FrontierMath (Tiers 1-3) | — | 72.2% |
| FrontierMath Tier 4 | — | 39% |
| MathArena Final-Answer Competitions | — | 87.8% |
| OTIS Mock AIME 2024-2025 | — | 97.2% |
| ProofBench | — | 87% |
Knowledge Kimi K3 leads
GLM-4.5: 35.5 (#172), Kimi K3: 63.2 (#19)
| Benchmark | GLM-4.5 | Kimi K3 |
|---|---|---|
| LMArena Expert | 1433 | 1520 |
| GPQA Diamond | — | 93.1% |
| Humanity's Last Exam | 8.3% | — |
| SimpleQA Verified | — | 50.6% |
| Confabulations | 11.3% | — |
Multimodal Not comparable
GLM-4.5: —, Kimi K3: 38.4 (#58)
| Benchmark | GLM-4.5 | Kimi K3 |
|---|---|---|
| Blueprint-Bench 2 | — | 29.5% |
| Furniture Assembly | — | 34.2% |
Multilingual Kimi K3 leads
GLM-4.5: 53.0 (#74), Kimi K3: 56.5 (#20)
| Benchmark | GLM-4.5 | Kimi K3 |
|---|---|---|
| LMArena Non-English | 1417 | 1466 |
| LMArena Chinese | 1465 | 1528 |
| LMArena French | 1423 | 1488 |
| LMArena German | 1406 | 1474 |
| LMArena Japanese | 1416 | 1492 |
| LMArena Korean | 1382 | 1465 |
| LMArena Russian | 1414 | 1481 |
| LMArena Spanish | 1454 | 1478 |
Instruction Following Kimi K3 leads
GLM-4.5: 74.3 (#100), Kimi K3: 77.8 (#13)
| Benchmark | GLM-4.5 | Kimi K3 |
|---|---|---|
| LMArena Instruction Following | 1405 | 1481 |
Long Context Kimi K3 leads
GLM-4.5: 38.2 (#196), Kimi K3: 45.8 (#27)
| Benchmark | GLM-4.5 | Kimi K3 |
|---|---|---|
| LMArena Longer Query | 1413 | 1494 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Kimi K3 leads
GLM-4.5: 57.7 (#121), Kimi K3: 76.7 (#4)
| Benchmark | GLM-4.5 | Kimi K3 |
|---|---|---|
| LMArena Text | 1430 | 1476 |
| LMArena Creative Writing | 1395 | 1452 |
| EQ-Bench Creative Writing | 1343 | 2082 |
| LMArena Multi-Turn | 1415 | 1488 |
| Short-Story Creative Writing | 73.4% | — |
| EQ-Bench 4 | — | 1339 |
Frequently asked questions
Is GLM-4.5 better than Kimi K3?
Kimi K3 is the stronger model overall, scoring 59.5 to 41.4 on the Noometry Index. GLM-4.5 costs 6.0× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Which is cheaper, GLM-4.5 or Kimi K3?
GLM-4.5 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Kimi K3 lists at $3 and $15.
Is GLM-4.5 or Kimi K3 better for coding?
Kimi K3 scores higher on coding benchmarks: 60.6 versus 41.1 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 131K.
How many benchmarks do GLM-4.5 and Kimi K3 share?
20 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Kimi K3 has 53.