Model comparison
GLM-4.6 vs Inkling
Inkling is the stronger model overall, scoring 44.1 to 41.4 on the Noometry Index. GLM-4.6 costs 2.6× less per token, which makes it the better buy when Inkling'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 3 categories and Inkling in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.4 to 23.7.
- The biggest single-benchmark swing is SciCode: 38.4% for GLM-4.6 and 47% for Inkling.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- GLM-4.6 accepts more context: 205K tokens versus 66K.
Side by side
| GLM-4.6 | Inkling | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Thinking Machines Lab |
| Noometry Index | 41.4 | 44.1 |
| Released | 2025-09-30 | 2026-07-15 |
| Weights | Open | Open |
| Context window | 205K | 66K |
| Max output | 131K | 66K |
| Input $ / M tokens | $0.60 | $1.87 |
| Output $ / M tokens | $2.20 | $4.68 |
| Results tracked | 29 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
GLM-4.6: 40.1 (#148), Inkling: 34.5 (#234)
| Benchmark | GLM-4.6 | Inkling |
|---|---|---|
| LMArena WebDev | 1340 | 1413 |
| SciCode | 38.4% | 47% |
| LMArena Coding | 1449 | 1464 |
| ALE-Bench | 340.82 | 946 |
| FrontierCode | — | 14% |
| SWE-bench Verified (bash only) | 55.4% | — |
| FrontierSWE | — | 4.1% |
| WeirdML | — | 32.3% |
Agentic & Tool Use GLM-4.6 leads
GLM-4.6: 32.3 (#66), Inkling: 29.6 (#85)
| Benchmark | GLM-4.6 | Inkling |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| APEX-Agents | — | 33.8% |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| τ²-bench Banking | — | 25% |
Reasoning Inkling leads
GLM-4.6: 23.7 (#172), Inkling: 40.4 (#56)
| Benchmark | GLM-4.6 | Inkling |
|---|---|---|
| CritPt | 1.1% | 5.4% |
| LMArena Hard Prompts | 1440 | 1451 |
| ARC-AGI-2 | — | 36.5% |
| SimpleBench | — | 50% |
| Kagi LLM Benchmark | 47.4% | — |
| ARC-AGI-1 | — | 79.5% |
| Chess Puzzles | — | 21% |
| DTBench | — | 87.5% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 148.54 |
Math GLM-4.6 leads
GLM-4.6: 39.1 (#111), Inkling: 31.3 (#225)
| Benchmark | GLM-4.6 | Inkling |
|---|---|---|
| LMArena Math | 1432 | 1479 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 0% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Inkling leads
GLM-4.6: 40.2 (#124), Inkling: 55.1 (#49)
| Benchmark | GLM-4.6 | Inkling |
|---|---|---|
| LMArena Expert | 1431 | 1465 |
| GPQA Diamond | — | 88.3% |
| SimpleQA Verified | — | 40.3% |
| Vectara Hallucination Rate | 9.5% | — |
Multilingual Too close to call
GLM-4.6: 53.5 (#66), Inkling: 54.0 (#52)
| Benchmark | GLM-4.6 | Inkling |
|---|---|---|
| LMArena Non-English | 1426 | 1434 |
| LMArena Chinese | 1499 | 1490 |
| LMArena French | 1459 | 1458 |
| LMArena German | 1447 | 1446 |
| LMArena Japanese | 1393 | 1429 |
| LMArena Korean | 1400 | 1404 |
| LMArena Russian | 1419 | 1429 |
| LMArena Spanish | 1436 | 1448 |
Instruction Following Too close to call
GLM-4.6: 74.3 (#98), Inkling: 75.1 (#71)
| Benchmark | GLM-4.6 | Inkling |
|---|---|---|
| LMArena Instruction Following | 1410 | 1426 |
Long Context Too close to call
GLM-4.6: 43.4 (#94), Inkling: 43.8 (#86)
| Benchmark | GLM-4.6 | Inkling |
|---|---|---|
| LMArena Longer Query | 1422 | 1434 |
Writing & Preference Inkling leads
GLM-4.6: 61.1 (#90), Inkling: 65.2 (#51)
| Benchmark | GLM-4.6 | Inkling |
|---|---|---|
| LMArena Text | 1440 | 1441 |
| LMArena Creative Writing | 1411 | 1387 |
| EQ-Bench Creative Writing | 1411 | 1611 |
| LMArena Multi-Turn | 1427 | 1436 |
| EQ-Bench 4 | — | 1226 |
Frequently asked questions
Is GLM-4.6 better than Inkling?
Inkling is the stronger model overall, scoring 44.1 to 41.4 on the Noometry Index. GLM-4.6 costs 2.6× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Which is cheaper, GLM-4.6 or Inkling?
GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Inkling lists at $1.87 and $4.68.
Is GLM-4.6 or Inkling better for coding?
GLM-4.6 scores higher on coding benchmarks: 40.1 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
GLM-4.6 does, with 205K tokens against 66K.
How many benchmarks do GLM-4.6 and Inkling share?
22 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Inkling has 41.