Model comparison
GLM-4.6 vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 40.9 on the Noometry Index.
Last verified . 21 shared benchmarks.
Summary
- They share 21 benchmarks with published results for both. GLM-4.6 scores higher in 4 categories and Inkling-Small in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 39.0 to 23.1.
- The biggest single-benchmark swing is SciCode: 38.4% for GLM-4.6 and 48.7% for Inkling-Small.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- Inkling-Small accepts more context: 524K tokens versus 205K.
Side by side
| GLM-4.6 | Inkling-Small | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Thinking Machines Lab |
| Noometry Index | 40.9 | 46.5 |
| Released | 2025-09-30 | 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 | 29 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
GLM-4.6: 39.9 (#137), Inkling-Small: 43.3 (#80)
| Benchmark | GLM-4.6 | Inkling-Small |
|---|---|---|
| LMArena WebDev | 1339 | 1408 |
| SciCode | 38.4% | 48.7% |
| LMArena Coding | 1449 | 1451 |
| SWE-bench Verified (bash only) | 55.4% | — |
| ALE-Bench | 340.82 | — |
Agentic & Tool Use Not comparable
GLM-4.6: 32.1 (#60), Inkling-Small: —
| Benchmark | GLM-4.6 | Inkling-Small |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
Reasoning Inkling-Small leads
GLM-4.6: 23.1 (#168), Inkling-Small: 39.0 (#53)
| Benchmark | GLM-4.6 | Inkling-Small |
|---|---|---|
| CritPt | 1.1% | 8.3% |
| LMArena Hard Prompts | 1440 | 1424 |
| ARC-AGI-2 | — | 40.1% |
| Kagi LLM Benchmark | 47.4% | — |
| ARC-AGI-1 | — | 84% |
| Chess Puzzles | — | 18% |
| Mystery Game Puzzles | — | 6% |
| Epoch Capabilities Index | — | 150.13 |
Math Inkling-Small leads
GLM-4.6: 36.4 (#115), Inkling-Small: 44.9 (#65)
| Benchmark | GLM-4.6 | Inkling-Small |
|---|---|---|
| LMArena Math | 1431 | 1453 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| OTIS Mock AIME 2024-2025 | — | 90% |
| ProofBench | — | 6% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Inkling-Small leads
GLM-4.6: 39.6 (#118), Inkling-Small: 48.3 (#71)
| Benchmark | GLM-4.6 | Inkling-Small |
|---|---|---|
| LMArena Expert | 1432 | 1442 |
| GPQA Diamond | — | 88.5% |
| SimpleQA Verified | — | 19.1% |
| Vectara Hallucination Rate | 9.5% | — |
Multimodal Not comparable
GLM-4.6: —, Inkling-Small: 38.4 (#59)
| Benchmark | GLM-4.6 | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |
Multilingual GLM-4.6 leads
GLM-4.6: 53.6 (#62), Inkling-Small: 51.7 (#102)
| Benchmark | GLM-4.6 | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1426 | 1400 |
| LMArena Chinese | 1500 | 1458 |
| LMArena French | 1459 | 1438 |
| LMArena German | 1447 | 1412 |
| LMArena Japanese | 1394 | 1399 |
| LMArena Korean | 1401 | 1355 |
| LMArena Russian | 1418 | 1392 |
| LMArena Spanish | 1436 | 1426 |
Instruction Following Too close to call
GLM-4.6: 74.5 (#93), Inkling-Small: 73.9 (#112)
| Benchmark | GLM-4.6 | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1410 | 1397 |
Long Context Too close to call
GLM-4.6: 43.4 (#91), Inkling-Small: 42.7 (#113)
| Benchmark | GLM-4.6 | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1423 | 1401 |
Writing & Preference GLM-4.6 leads
GLM-4.6: 61.3 (#86), Inkling-Small: 59.8 (#102)
| Benchmark | GLM-4.6 | Inkling-Small |
|---|---|---|
| LMArena Text | 1440 | 1413 |
| LMArena Creative Writing | 1411 | 1330 |
| EQ-Bench Creative Writing | 1411 | 1491 |
| LMArena Multi-Turn | 1427 | 1420 |
Frequently asked questions
Is GLM-4.6 better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 40.9 on the Noometry Index.
Which is cheaper, GLM-4.6 or Inkling-Small?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.
Is GLM-4.6 or Inkling-Small better for coding?
Inkling-Small scores higher on coding benchmarks: 43.3 versus 39.9 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 205K.
How many benchmarks do GLM-4.6 and Inkling-Small share?
21 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Inkling-Small has 33.