Model comparison
GLM-4.5 vs Inkling
Inkling is the stronger model overall, scoring 44.1 to 41.4 on the Noometry Index. GLM-4.5 costs 2.6× less per token, which makes it the better buy when Inkling'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 2 categories and Inkling in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.2 to 35.5.
- The biggest single-benchmark swing is WeirdML: 40.6% for GLM-4.5 and 32.3% for Inkling.
- GLM-4.5 is cheaper at $0.60 / $2.20 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- GLM-4.5 accepts more context: 131K tokens versus 66K.
Side by side
| GLM-4.5 | Inkling | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Thinking Machines Lab |
| Noometry Index | 41.4 | 44.1 |
| Released | 2025-07-27 | 2026-07-15 |
| Weights | Open | Open |
| Context window | 131K | 66K |
| Max output | 98K | 66K |
| Input $ / M tokens | $0.60 | $1.87 |
| Output $ / M tokens | $2.20 | $4.68 |
| Results tracked | 27 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5 leads
GLM-4.5: 41.1 (#121), Inkling: 34.1 (#229)
| Benchmark | GLM-4.5 | Inkling |
|---|---|---|
| WeirdML | 40.6% | 32.3% |
| LMArena Coding | 1434 | 1463 |
| ALE-Bench | 344.82 | 946 |
| FrontierCode | — | 14% |
| SWE-bench Verified (bash only) | 54.2% | — |
| LMArena WebDev | — | 1412 |
| FrontierSWE | — | 4.1% |
| SciCode | — | 47% |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Not comparable
GLM-4.5: —, Inkling: 29.5 (#76)
| Benchmark | GLM-4.5 | Inkling |
|---|---|---|
| APEX-Agents | — | 33.8% |
| τ²-bench Banking | — | 25% |
Reasoning Inkling leads
GLM-4.5: 27.7 (#99), Inkling: 40.6 (#48)
| Benchmark | GLM-4.5 | Inkling |
|---|---|---|
| LMArena Hard Prompts | 1430 | 1452 |
| ARC-AGI-2 | — | 36.5% |
| SimpleBench | — | 50% |
| Kagi LLM Benchmark | 57.9% | — |
| ARC-AGI-1 | — | 79.5% |
| CritPt | — | 5.4% |
| Chess Puzzles | — | 21% |
| DTBench | — | 87.5% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 148.6 |
Math GLM-4.5 leads
GLM-4.5: 36.3 (#119), Inkling: 31.2 (#198)
| Benchmark | GLM-4.5 | Inkling |
|---|---|---|
| LMArena Math | 1427 | 1482 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 0% |
Knowledge Inkling leads
GLM-4.5: 35.5 (#172), Inkling: 55.2 (#44)
| Benchmark | GLM-4.5 | Inkling |
|---|---|---|
| LMArena Expert | 1433 | 1468 |
| GPQA Diamond | — | 88.3% |
| Humanity's Last Exam | 8.3% | — |
| SimpleQA Verified | — | 40.3% |
| Confabulations | 11.3% | — |
Multilingual Inkling leads
GLM-4.5: 53.0 (#74), Inkling: 54.2 (#49)
| Benchmark | GLM-4.5 | Inkling |
|---|---|---|
| LMArena Non-English | 1417 | 1434 |
| LMArena Chinese | 1465 | 1495 |
| LMArena French | 1423 | 1453 |
| LMArena German | 1406 | 1456 |
| LMArena Japanese | 1416 | 1428 |
| LMArena Korean | 1382 | 1401 |
| LMArena Russian | 1414 | 1430 |
| LMArena Spanish | 1454 | 1442 |
Instruction Following Inkling leads
GLM-4.5: 74.3 (#100), Inkling: 75.3 (#65)
| Benchmark | GLM-4.5 | Inkling |
|---|---|---|
| LMArena Instruction Following | 1405 | 1427 |
Long Context Inkling leads
GLM-4.5: 38.2 (#196), Inkling: 43.9 (#79)
| Benchmark | GLM-4.5 | Inkling |
|---|---|---|
| LMArena Longer Query | 1413 | 1436 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Inkling leads
GLM-4.5: 57.7 (#121), Inkling: 65.5 (#48)
| Benchmark | GLM-4.5 | Inkling |
|---|---|---|
| LMArena Text | 1430 | 1443 |
| LMArena Creative Writing | 1395 | 1390 |
| EQ-Bench Creative Writing | 1343 | 1611 |
| LMArena Multi-Turn | 1415 | 1436 |
| Short-Story Creative Writing | 73.4% | — |
| EQ-Bench 4 | — | 1226 |
Frequently asked questions
Is GLM-4.5 better than Inkling?
Inkling is the stronger model overall, scoring 44.1 to 41.4 on the Noometry Index. GLM-4.5 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-4.5 or Inkling?
GLM-4.5 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-4.5 or Inkling better for coding?
GLM-4.5 scores higher on coding benchmarks: 41.1 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
GLM-4.5 does, with 131K tokens against 66K.
How many benchmarks do GLM-4.5 and Inkling share?
20 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Inkling has 41.