Model comparison
GLM-4.7 vs Granite 3.1 2b Instruct
GLM-4.7 is the stronger model overall, scoring 42.0 to 33.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. GLM-4.7 scores higher in 8 categories and Granite 3.1 2b Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.7 leads 60.9 to 34.1.
Side by side
| GLM-4.7 | Granite 3.1 2b Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | IBM |
| Noometry Index | 42.0 | 33.2 |
| Released | 2025-12-22 | — |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 36 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.7 leads
GLM-4.7: 44.0 (#79), Granite 3.1 2b Instruct: 33.4 (#257)
| Benchmark | GLM-4.7 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Coding | 1454 | 1149 |
| LMArena WebDev | 1435 | — |
| SciCode | 45.1% | — |
| ALE-Bench | 399.48 | — |
Agentic & Tool Use Not comparable
GLM-4.7: 26.5 (#103), Granite 3.1 2b Instruct: —
| Benchmark | GLM-4.7 | Granite 3.1 2b Instruct |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| Vending-Bench 2 | 2,377 | — |
Reasoning GLM-4.7 leads
GLM-4.7: 24.3 (#164), Granite 3.1 2b Instruct: 22.0 (#209)
| Benchmark | GLM-4.7 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1138 |
| SimpleBench | 47.7% | — |
| CritPt | 1.7% | — |
| Chess Puzzles | 6% | — |
| Epoch Capabilities Index | 143.51 | — |
Math GLM-4.7 leads
GLM-4.7: 38.6 (#135), Granite 3.1 2b Instruct: 33.1 (#206)
| Benchmark | GLM-4.7 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Math | 1423 | 1159 |
| OTIS Mock AIME 2024-2025 | 83.3% | — |
| ProofBench | 6% | — |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GLM-4.7 leads
GLM-4.7: 47.0 (#80), Granite 3.1 2b Instruct: 30.8 (#224)
| Benchmark | GLM-4.7 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Expert | 1424 | 1131 |
| GPQA Diamond | 83.3% | — |
| SimpleQA Verified | 32.2% | — |
| Vectara Hallucination Rate | 11.7% | — |
Multilingual GLM-4.7 leads
GLM-4.7: 52.8 (#79), Granite 3.1 2b Instruct: 29.1 (#269)
| Benchmark | GLM-4.7 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Non-English | 1417 | 1068 |
| LMArena Chinese | 1495 | 1139 |
| LMArena Russian | 1423 | 1063 |
| LMArena French | 1432 | — |
| LMArena German | 1424 | — |
| LMArena Japanese | 1439 | — |
| LMArena Korean | 1399 | — |
| LMArena Spanish | 1434 | — |
Instruction Following GLM-4.7 leads
GLM-4.7: 74.4 (#95), Granite 3.1 2b Instruct: 57.7 (#264)
| Benchmark | GLM-4.7 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Instruction Following | 1411 | 1116 |
Long Context GLM-4.7 leads
GLM-4.7: 42.8 (#116), Granite 3.1 2b Instruct: 35.0 (#244)
| Benchmark | GLM-4.7 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Longer Query | 1432 | 1155 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
Writing & Preference GLM-4.7 leads
GLM-4.7: 60.9 (#93), Granite 3.1 2b Instruct: 34.1 (#274)
| Benchmark | GLM-4.7 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Text | 1435 | 1127 |
| LMArena Creative Writing | 1401 | 1116 |
| LMArena Multi-Turn | 1446 | 1099 |
| EQ-Bench Creative Writing | 1413 | — |
Frequently asked questions
Is GLM-4.7 better than Granite 3.1 2b Instruct?
GLM-4.7 is the stronger model overall, scoring 42.0 to 33.2 on the Noometry Index.
Is GLM-4.7 or Granite 3.1 2b Instruct better for coding?
GLM-4.7 scores higher on coding benchmarks: 44.0 versus 33.4 in the Noometry coding category.
How many benchmarks do GLM-4.7 and Granite 3.1 2b Instruct share?
12 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Granite 3.1 2b Instruct has 12.