Model comparison
GLM-4.6 vs Granite 3.1 8b Instruct
GLM-4.6 is the stronger model overall, scoring 40.9 to 31.8 on the Noometry Index.
Last verified . 13 shared benchmarks.
Summary
- They share 13 benchmarks with published results for both. GLM-4.6 scores higher in 9 categories and Granite 3.1 8b Instruct in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.6 leads 61.3 to 35.7.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 72.4% for GLM-4.6 and 27.1% for Granite 3.1 8b Instruct.
Side by side
| GLM-4.6 | Granite 3.1 8b Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | IBM |
| Noometry Index | 40.9 | 31.8 |
| Released | 2025-09-30 | — |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 29 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
GLM-4.6: 39.9 (#137), Granite 3.1 8b Instruct: 33.9 (#232)
| Benchmark | GLM-4.6 | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Coding | 1449 | 1186 |
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1339 | — |
| SciCode | 38.4% | — |
| ALE-Bench | 340.82 | — |
Agentic & Tool Use GLM-4.6 leads
GLM-4.6: 32.1 (#60), Granite 3.1 8b Instruct: 23.9 (#113)
| Benchmark | GLM-4.6 | Granite 3.1 8b Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 72.4% | 27.1% |
| Terminal-Bench | 24.5% | — |
Reasoning GLM-4.6 leads
GLM-4.6: 23.1 (#168), Granite 3.1 8b Instruct: 21.2 (#204)
| Benchmark | GLM-4.6 | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1440 | 1146 |
| Kagi LLM Benchmark | 47.4% | — |
| CritPt | 1.1% | — |
Math GLM-4.6 leads
GLM-4.6: 36.4 (#115), Granite 3.1 8b Instruct: 30.4 (#210)
| Benchmark | GLM-4.6 | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Math | 1431 | 1152 |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-4.6 leads
GLM-4.6: 39.6 (#118), Granite 3.1 8b Instruct: 30.6 (#218)
| Benchmark | GLM-4.6 | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Expert | 1432 | 1142 |
| Vectara Hallucination Rate | 9.5% | — |
Multilingual GLM-4.6 leads
GLM-4.6: 53.6 (#62), Granite 3.1 8b Instruct: 31.1 (#255)
| Benchmark | GLM-4.6 | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Non-English | 1426 | 1099 |
| LMArena Chinese | 1500 | 1145 |
| LMArena Russian | 1418 | 1092 |
| LMArena French | 1459 | — |
| LMArena German | 1447 | — |
| LMArena Japanese | 1394 | — |
| LMArena Korean | 1401 | — |
| LMArena Spanish | 1436 | — |
Instruction Following GLM-4.6 leads
GLM-4.6: 74.5 (#93), Granite 3.1 8b Instruct: 58.9 (#254)
| Benchmark | GLM-4.6 | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Instruction Following | 1410 | 1131 |
Long Context GLM-4.6 leads
GLM-4.6: 43.4 (#91), Granite 3.1 8b Instruct: 35.2 (#236)
| Benchmark | GLM-4.6 | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Longer Query | 1423 | 1162 |
Writing & Preference GLM-4.6 leads
GLM-4.6: 61.3 (#86), Granite 3.1 8b Instruct: 35.7 (#261)
| Benchmark | GLM-4.6 | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Text | 1440 | 1150 |
| LMArena Creative Writing | 1411 | 1129 |
| LMArena Multi-Turn | 1427 | 1108 |
| EQ-Bench Creative Writing | 1411 | — |
Frequently asked questions
Is GLM-4.6 better than Granite 3.1 8b Instruct?
GLM-4.6 is the stronger model overall, scoring 40.9 to 31.8 on the Noometry Index.
Is GLM-4.6 or Granite 3.1 8b Instruct better for coding?
GLM-4.6 scores higher on coding benchmarks: 39.9 versus 33.9 in the Noometry coding category.
How many benchmarks do GLM-4.6 and Granite 3.1 8b Instruct share?
13 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Granite 3.1 8b Instruct has 13.