Model comparison
GLM-4.7 vs Granite 4.1 8b
GLM-4.7 is the stronger model overall, scoring 42.0 to 37.4 on the Noometry Index.
Last verified . 13 shared benchmarks.
Summary
- They share 13 benchmarks with published results for both. GLM-4.7 scores higher in 7 categories and Granite 4.1 8b in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where GLM-4.7 leads 44.0 to 30.1.
Side by side
| GLM-4.7 | Granite 4.1 8b | |
|---|---|---|
| Provider | Z.ai (Zhipu) | IBM |
| Noometry Index | 42.0 | 37.4 |
| 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 | 13 |
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 4.1 8b: 30.1 (#297)
| Benchmark | GLM-4.7 | Granite 4.1 8b |
|---|---|---|
| LMArena WebDev | 1435 | 1192 |
| LMArena Coding | 1454 | 1312 |
| SciCode | 45.1% | — |
| ALE-Bench | 399.48 | — |
Agentic & Tool Use Not comparable
GLM-4.7: 26.5 (#103), Granite 4.1 8b: —
| Benchmark | GLM-4.7 | Granite 4.1 8b |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| Vending-Bench 2 | 2,377 | — |
Reasoning Granite 4.1 8b leads
GLM-4.7: 24.3 (#164), Granite 4.1 8b: 25.7 (#143)
| Benchmark | GLM-4.7 | Granite 4.1 8b |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1293 |
| 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 4.1 8b: 36.4 (#166)
| Benchmark | GLM-4.7 | Granite 4.1 8b |
|---|---|---|
| LMArena Math | 1423 | 1312 |
| 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 4.1 8b: 36.1 (#174)
| Benchmark | GLM-4.7 | Granite 4.1 8b |
|---|---|---|
| LMArena Expert | 1424 | 1309 |
| 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 4.1 8b: 41.7 (#204)
| Benchmark | GLM-4.7 | Granite 4.1 8b |
|---|---|---|
| LMArena Non-English | 1417 | 1261 |
| LMArena Chinese | 1495 | 1337 |
| LMArena Russian | 1423 | 1240 |
| 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 4.1 8b: 66.9 (#203)
| Benchmark | GLM-4.7 | Granite 4.1 8b |
|---|---|---|
| LMArena Instruction Following | 1411 | 1269 |
Long Context GLM-4.7 leads
GLM-4.7: 42.8 (#116), Granite 4.1 8b: 38.7 (#193)
| Benchmark | GLM-4.7 | Granite 4.1 8b |
|---|---|---|
| LMArena Longer Query | 1432 | 1275 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
Writing & Preference GLM-4.7 leads
GLM-4.7: 60.9 (#93), Granite 4.1 8b: 48.1 (#204)
| Benchmark | GLM-4.7 | Granite 4.1 8b |
|---|---|---|
| LMArena Text | 1435 | 1290 |
| LMArena Creative Writing | 1401 | 1251 |
| LMArena Multi-Turn | 1446 | 1268 |
| EQ-Bench Creative Writing | 1413 | — |
Frequently asked questions
Is GLM-4.7 better than Granite 4.1 8b?
GLM-4.7 is the stronger model overall, scoring 42.0 to 37.4 on the Noometry Index.
Is GLM-4.7 or Granite 4.1 8b better for coding?
GLM-4.7 scores higher on coding benchmarks: 44.0 versus 30.1 in the Noometry coding category.
How many benchmarks do GLM-4.7 and Granite 4.1 8b share?
13 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Granite 4.1 8b has 13.