Model comparison
GLM-4.7 vs Inkling
Inkling is the stronger model overall, scoring 44.1 to 41.7 on the Noometry Index. GLM-4.7 costs 2.6× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. GLM-4.7 scores higher in 2 categories and Inkling in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.6 to 23.7.
- The biggest single-benchmark swing is Chess Puzzles: 6% for GLM-4.7 and 21% for Inkling.
- GLM-4.7 is cheaper at $0.60 / $2.20 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- GLM-4.7 accepts more context: 205K tokens versus 66K.
Side by side
| GLM-4.7 | Inkling | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Thinking Machines Lab |
| Noometry Index | 41.7 | 44.1 |
| Released | 2025-12-22 | 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 | 36 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.7 leads
GLM-4.7: 43.6 (#74), Inkling: 34.1 (#229)
| Benchmark | GLM-4.7 | Inkling |
|---|---|---|
| LMArena WebDev | 1435 | 1412 |
| SciCode | 45.1% | 47% |
| LMArena Coding | 1454 | 1463 |
| ALE-Bench | 399.48 | 946 |
| FrontierCode | — | 14% |
| FrontierSWE | — | 4.1% |
| WeirdML | — | 32.3% |
Agentic & Tool Use Inkling leads
GLM-4.7: 26.4 (#96), Inkling: 29.5 (#76)
| Benchmark | GLM-4.7 | Inkling |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| APEX-Agents | — | 33.8% |
| τ²-bench Banking | — | 25% |
| Vending-Bench 2 | 2,377 | — |
Reasoning Inkling leads
GLM-4.7: 23.7 (#161), Inkling: 40.6 (#48)
| Benchmark | GLM-4.7 | Inkling |
|---|---|---|
| SimpleBench | 47.7% | 50% |
| CritPt | 1.7% | 5.4% |
| Chess Puzzles | 6% | 21% |
| LMArena Hard Prompts | 1443 | 1452 |
| Epoch Capabilities Index | 143.53 | 148.6 |
| ARC-AGI-2 | — | 36.5% |
| ARC-AGI-1 | — | 79.5% |
| DTBench | — | 87.5% |
| LMCA | — | 37.6% |
Math GLM-4.7 leads
GLM-4.7: 37.7 (#92), Inkling: 31.2 (#198)
| Benchmark | GLM-4.7 | Inkling |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 88.9% |
| ProofBench | 6% | 0% |
| LMArena Math | 1423 | 1482 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Inkling leads
GLM-4.7: 47.0 (#74), Inkling: 55.2 (#44)
| Benchmark | GLM-4.7 | Inkling |
|---|---|---|
| GPQA Diamond | 83.3% | 88.3% |
| SimpleQA Verified | 32.2% | 40.3% |
| LMArena Expert | 1424 | 1468 |
| Vectara Hallucination Rate | 11.7% | — |
Multilingual Inkling leads
GLM-4.7: 53.0 (#75), Inkling: 54.2 (#49)
| Benchmark | GLM-4.7 | Inkling |
|---|---|---|
| LMArena Non-English | 1417 | 1434 |
| LMArena Chinese | 1495 | 1495 |
| LMArena French | 1432 | 1453 |
| LMArena German | 1426 | 1456 |
| LMArena Japanese | 1439 | 1428 |
| LMArena Korean | 1401 | 1401 |
| LMArena Russian | 1423 | 1430 |
| LMArena Spanish | 1433 | 1442 |
Instruction Following Too close to call
GLM-4.7: 74.6 (#90), Inkling: 75.3 (#65)
| Benchmark | GLM-4.7 | Inkling |
|---|---|---|
| LMArena Instruction Following | 1411 | 1427 |
Long Context Inkling leads
GLM-4.7: 42.8 (#111), Inkling: 43.9 (#79)
| Benchmark | GLM-4.7 | Inkling |
|---|---|---|
| LMArena Longer Query | 1432 | 1436 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
Writing & Preference Inkling leads
GLM-4.7: 61.1 (#89), Inkling: 65.5 (#48)
| Benchmark | GLM-4.7 | Inkling |
|---|---|---|
| LMArena Text | 1436 | 1443 |
| LMArena Creative Writing | 1401 | 1390 |
| EQ-Bench Creative Writing | 1413 | 1611 |
| LMArena Multi-Turn | 1446 | 1436 |
| EQ-Bench 4 | — | 1226 |
Frequently asked questions
Is GLM-4.7 better than Inkling?
Inkling is the stronger model overall, scoring 44.1 to 41.7 on the Noometry Index. GLM-4.7 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-4.7 or Inkling?
GLM-4.7 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-4.7 or Inkling better for coding?
GLM-4.7 scores higher on coding benchmarks: 43.6 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
GLM-4.7 does, with 205K tokens against 66K.
How many benchmarks do GLM-4.7 and Inkling share?
29 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Inkling has 41.