Model comparison
GLM-5.1 vs Inkling-Small
GLM-5.1 is the stronger model overall, scoring 47.8 to 46.5 on the Noometry Index. Inkling-Small costs 3.4× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Last verified . 28 shared benchmarks.
Summary
- They share 28 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and Inkling-Small in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5.1 leads 66.9 to 59.6.
- The biggest single-benchmark swing is ProofBench: 22.2% for GLM-5.1 and 6% for Inkling-Small.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- Inkling-Small accepts more context: 524K tokens versus 200K.
Side by side
| GLM-5.1 | Inkling-Small | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Thinking Machines Lab |
| Noometry Index | 47.8 | 46.5 |
| Released | 2026-04-07 | 2026-07-15 |
| Weights | Open | Open |
| Context window | 200K | 524K |
| Max output | 131K | 1.05M |
| Input $ / M tokens | $1.40 | $0.45 |
| Output $ / M tokens | $4.40 | $1.20 |
| Results tracked | 41 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
GLM-5.1: 48.7 (#55), Inkling-Small: 43.6 (#85)
| Benchmark | GLM-5.1 | Inkling-Small |
|---|---|---|
| LMArena WebDev | 1508 | 1409 |
| SciCode | 43.8% | 48.7% |
| LMArena Coding | 1485 | 1451 |
| SWE-bench Verified | 74.2% | — |
| WeirdML | 57.1% | — |
| ALE-Bench | 887.1 | — |
Agentic & Tool Use Not comparable
GLM-5.1: 24.9 (#113), Inkling-Small: —
| Benchmark | GLM-5.1 | Inkling-Small |
|---|---|---|
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |
Reasoning Too close to call
GLM-5.1: 39.1 (#60), Inkling-Small: 38.6 (#63)
| Benchmark | GLM-5.1 | Inkling-Small |
|---|---|---|
| CritPt | 4.6% | 8.3% |
| Chess Puzzles | 19% | 18% |
| LMArena Hard Prompts | 1472 | 1423 |
| Epoch Capabilities Index | 149.84 | 150.15 |
| ARC-AGI-2 | — | 40.1% |
| SimpleBench | 55.1% | — |
| NYT Connections (extended) | 77.7% | — |
| ARC-AGI-1 | — | 84% |
| Thematic Generalization | 69.8% | — |
| Mystery Game Puzzles | — | 6% |
Math GLM-5.1 leads
GLM-5.1: 49.7 (#60), Inkling-Small: 45.1 (#77)
| Benchmark | GLM-5.1 | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.8% | 46.3% |
| OTIS Mock AIME 2024-2025 | 93.3% | 90% |
| ProofBench | 22.2% | 6% |
| LMArena Math | 1473 | 1459 |
| FrontierMath Tier 4 | — | 17.1% |
| MathArena Final-Answer Competitions | 67.1% | — |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GLM-5.1 leads
GLM-5.1: 54.9 (#50), Inkling-Small: 48.2 (#77)
| Benchmark | GLM-5.1 | Inkling-Small |
|---|---|---|
| GPQA Diamond | 89.9% | 88.5% |
| SimpleQA Verified | 34% | 19.1% |
| LMArena Expert | 1476 | 1442 |
Multimodal Not comparable
GLM-5.1: —, Inkling-Small: 39.1 (#62)
| Benchmark | GLM-5.1 | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), Inkling-Small: 51.7 (#104)
| Benchmark | GLM-5.1 | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1447 | 1402 |
| LMArena Chinese | 1515 | 1465 |
| LMArena French | 1474 | 1436 |
| LMArena German | 1465 | 1405 |
| LMArena Japanese | 1434 | 1405 |
| LMArena Korean | 1418 | 1363 |
| LMArena Russian | 1454 | 1391 |
| LMArena Spanish | 1469 | 1428 |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.3 (#42), Inkling-Small: 73.8 (#114)
| Benchmark | GLM-5.1 | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1451 | 1399 |
Long Context GLM-5.1 leads
GLM-5.1: 44.9 (#53), Inkling-Small: 42.7 (#118)
| Benchmark | GLM-5.1 | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1466 | 1401 |
Writing & Preference GLM-5.1 leads
GLM-5.1: 66.9 (#31), Inkling-Small: 59.6 (#107)
| Benchmark | GLM-5.1 | Inkling-Small |
|---|---|---|
| LMArena Text | 1461 | 1414 |
| LMArena Creative Writing | 1453 | 1331 |
| EQ-Bench Creative Writing | 1592 | 1491 |
| LMArena Multi-Turn | 1472 | 1418 |
Frequently asked questions
Is GLM-5.1 better than Inkling-Small?
GLM-5.1 is the stronger model overall, scoring 47.8 to 46.5 on the Noometry Index. Inkling-Small costs 3.4× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Which is cheaper, GLM-5.1 or Inkling-Small?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.
Is GLM-5.1 or Inkling-Small better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 43.6 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 200K.
How many benchmarks do GLM-5.1 and Inkling-Small share?
28 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Inkling-Small has 33.