Model comparison
GLM-4.7 vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 42.0 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. GLM-4.7 scores higher in 5 categories and Inkling-Small in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 24.3.
- The biggest single-benchmark swing is SimpleQA Verified: 32.2% for GLM-4.7 and 19.1% for Inkling-Small.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
- Inkling-Small accepts more context: 524K tokens versus 205K.
Side by side
| GLM-4.7 | Inkling-Small | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Thinking Machines Lab |
| Noometry Index | 42.0 | 46.5 |
| Released | 2025-12-22 | 2026-07-15 |
| Weights | Open | Open |
| Context window | 205K | 524K |
| Max output | 131K | 1.05M |
| Input $ / M tokens | $0.60 | $0.45 |
| Output $ / M tokens | $2.20 | $1.20 |
| Results tracked | 36 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-4.7: 44.0 (#79), Inkling-Small: 43.6 (#85)
| Benchmark | GLM-4.7 | Inkling-Small |
|---|---|---|
| LMArena WebDev | 1435 | 1409 |
| SciCode | 45.1% | 48.7% |
| LMArena Coding | 1454 | 1451 |
| ALE-Bench | 399.48 | — |
Agentic & Tool Use Not comparable
GLM-4.7: 26.5 (#103), Inkling-Small: —
| Benchmark | GLM-4.7 | Inkling-Small |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| Vending-Bench 2 | 2,377 | — |
Reasoning Inkling-Small leads
GLM-4.7: 24.3 (#164), Inkling-Small: 38.6 (#63)
| Benchmark | GLM-4.7 | Inkling-Small |
|---|---|---|
| CritPt | 1.7% | 8.3% |
| Chess Puzzles | 6% | 18% |
| LMArena Hard Prompts | 1443 | 1423 |
| Epoch Capabilities Index | 143.51 | 150.15 |
| ARC-AGI-2 | — | 40.1% |
| SimpleBench | 47.7% | — |
| ARC-AGI-1 | — | 84% |
| Mystery Game Puzzles | — | 6% |
Math Inkling-Small leads
GLM-4.7: 38.6 (#135), Inkling-Small: 45.1 (#77)
| Benchmark | GLM-4.7 | Inkling-Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 90% |
| ProofBench | 6% | 6% |
| LMArena Math | 1423 | 1459 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Inkling-Small leads
GLM-4.7: 47.0 (#80), Inkling-Small: 48.2 (#77)
| Benchmark | GLM-4.7 | Inkling-Small |
|---|---|---|
| GPQA Diamond | 83.3% | 88.5% |
| SimpleQA Verified | 32.2% | 19.1% |
| LMArena Expert | 1424 | 1442 |
| Vectara Hallucination Rate | 11.7% | — |
Multimodal Not comparable
GLM-4.7: —, Inkling-Small: 39.1 (#62)
| Benchmark | GLM-4.7 | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |
Multilingual GLM-4.7 leads
GLM-4.7: 52.8 (#79), Inkling-Small: 51.7 (#104)
| Benchmark | GLM-4.7 | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1417 | 1402 |
| LMArena Chinese | 1495 | 1465 |
| LMArena French | 1432 | 1436 |
| LMArena German | 1424 | 1405 |
| LMArena Japanese | 1439 | 1405 |
| LMArena Korean | 1399 | 1363 |
| LMArena Russian | 1423 | 1391 |
| LMArena Spanish | 1434 | 1428 |
Instruction Following Too close to call
GLM-4.7: 74.4 (#95), Inkling-Small: 73.8 (#114)
| Benchmark | GLM-4.7 | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1411 | 1399 |
Long Context Too close to call
GLM-4.7: 42.8 (#116), Inkling-Small: 42.7 (#118)
| Benchmark | GLM-4.7 | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1432 | 1401 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
Writing & Preference GLM-4.7 leads
GLM-4.7: 60.9 (#93), Inkling-Small: 59.6 (#107)
| Benchmark | GLM-4.7 | Inkling-Small |
|---|---|---|
| LMArena Text | 1435 | 1414 |
| LMArena Creative Writing | 1401 | 1331 |
| EQ-Bench Creative Writing | 1413 | 1491 |
| LMArena Multi-Turn | 1446 | 1418 |
Frequently asked questions
Is GLM-4.7 better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 42.0 on the Noometry Index.
Which is cheaper, GLM-4.7 or Inkling-Small?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.
Is GLM-4.7 or Inkling-Small better for coding?
They score almost the same on coding (44.0 vs 43.6); test both on your own repository before choosing.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 205K.
How many benchmarks do GLM-4.7 and Inkling-Small share?
27 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Inkling-Small has 33.