Model comparison
GLM-4.6 vs Kimi K3
Kimi K3 is the stronger model overall, scoring 59.5 to 41.4 on the Noometry Index. GLM-4.6 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 . 22 shared benchmarks.
Summary
- They share 22 benchmarks with published results for both. GLM-4.6 scores higher in 0 categories and Kimi K3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K3 leads 63.0 to 23.7.
- The biggest single-benchmark swing is CritPt: 1.1% for GLM-4.6 and 23.4% for Kimi K3.
- GLM-4.6 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 205K.
Side by side
| GLM-4.6 | Kimi K3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Moonshot AI |
| Noometry Index | 41.4 | 59.5 |
| Released | 2025-09-30 | 2026-07-16 |
| Weights | Open | Open |
| Context window | 205K | 1.05M |
| Max output | 131K | 1.05M |
| Input $ / M tokens | $0.60 | $3 |
| Output $ / M tokens | $2.20 | $15 |
| Results tracked | 29 | 53 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
GLM-4.6: 40.1 (#148), Kimi K3: 61.0 (#10)
| Benchmark | GLM-4.6 | Kimi K3 |
|---|---|---|
| LMArena WebDev | 1340 | 1654 |
| SciCode | 38.4% | 59.5% |
| LMArena Coding | 1449 | 1508 |
| ALE-Bench | 340.82 | 1,524 |
| DeepSWE | — | 68.5% |
| FrontierCode | — | 44.2% |
| SWE-bench Verified (bash only) | 55.4% | — |
| FrontierSWE | — | 25.9% |
| WeirdML | — | 82.6% |
Agentic & Tool Use Kimi K3 leads
GLM-4.6: 32.3 (#66), Kimi K3: 41.8 (#20)
| Benchmark | GLM-4.6 | Kimi K3 |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| APEX-Agents | — | 50.6% |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| τ²-bench Banking | — | 37.1% |
| PostTrainBench | — | 32% |
| GBAEval | — | 48.3% |
| GDP.pdf | — | 19% |
| Vending-Bench 2 | — | 5,165 |
Reasoning Kimi K3 leads
GLM-4.6: 23.7 (#172), Kimi K3: 63.0 (#17)
| Benchmark | GLM-4.6 | Kimi K3 |
|---|---|---|
| CritPt | 1.1% | 23.4% |
| LMArena Hard Prompts | 1440 | 1496 |
| ARC-AGI-2 | — | 60.4% |
| SimpleBench | — | 60.7% |
| Kagi LLM Benchmark | 47.4% | — |
| NYT Connections (extended) | — | 93.6% |
| ARC-AGI-1 | — | 94.5% |
| Chess Puzzles | — | 39% |
| Mystery Game Puzzles | — | 26% |
| DTBench | — | 91.2% |
| LMCA | — | 52.7% |
| Surface Evolver Bench | — | 95% |
| Epoch Capabilities Index | — | 157.45 |
| ForecastBench | — | 61.1 |
Math Kimi K3 leads
GLM-4.6: 39.1 (#111), Kimi K3: 74.2 (#16)
| Benchmark | GLM-4.6 | Kimi K3 |
|---|---|---|
| LMArena Math | 1432 | 1491 |
| 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% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Kimi K3 leads
GLM-4.6: 40.2 (#124), Kimi K3: 63.2 (#21)
| Benchmark | GLM-4.6 | Kimi K3 |
|---|---|---|
| LMArena Expert | 1431 | 1521 |
| GPQA Diamond | — | 93.1% |
| SimpleQA Verified | — | 50.6% |
| Vectara Hallucination Rate | 9.5% | — |
Multimodal Not comparable
GLM-4.6: —, Kimi K3: 37.8 (#70)
| Benchmark | GLM-4.6 | Kimi K3 |
|---|---|---|
| Blueprint-Bench 2 | — | 29.5% |
| Furniture Assembly | — | 34.2% |
Multilingual Kimi K3 leads
GLM-4.6: 53.5 (#66), Kimi K3: 56.3 (#21)
| Benchmark | GLM-4.6 | Kimi K3 |
|---|---|---|
| LMArena Non-English | 1426 | 1466 |
| LMArena Chinese | 1499 | 1529 |
| LMArena French | 1459 | 1491 |
| LMArena German | 1447 | 1488 |
| LMArena Japanese | 1393 | 1487 |
| LMArena Korean | 1400 | 1458 |
| LMArena Russian | 1419 | 1482 |
| LMArena Spanish | 1436 | 1472 |
Instruction Following Kimi K3 leads
GLM-4.6: 74.3 (#98), Kimi K3: 77.7 (#14)
| Benchmark | GLM-4.6 | Kimi K3 |
|---|---|---|
| LMArena Instruction Following | 1410 | 1483 |
Long Context Kimi K3 leads
GLM-4.6: 43.4 (#94), Kimi K3: 45.8 (#29)
| Benchmark | GLM-4.6 | Kimi K3 |
|---|---|---|
| LMArena Longer Query | 1422 | 1494 |
Writing & Preference Kimi K3 leads
GLM-4.6: 61.1 (#90), Kimi K3: 76.6 (#4)
| Benchmark | GLM-4.6 | Kimi K3 |
|---|---|---|
| LMArena Text | 1440 | 1476 |
| LMArena Creative Writing | 1411 | 1454 |
| EQ-Bench Creative Writing | 1411 | 2082 |
| LMArena Multi-Turn | 1427 | 1488 |
| EQ-Bench 4 | — | 1339 |
Frequently asked questions
Is GLM-4.6 better than Kimi K3?
Kimi K3 is the stronger model overall, scoring 59.5 to 41.4 on the Noometry Index. GLM-4.6 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-4.6 or Kimi K3?
GLM-4.6 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-4.6 or Kimi K3 better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 205K.
How many benchmarks do GLM-4.6 and Kimi K3 share?
22 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Kimi K3 has 53.