Model comparison
GLM-4.7-Flash vs Granite 3.0 8b Instruct
GLM-4.7-Flash is the stronger model overall, scoring 38.8 to 31.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. GLM-4.7-Flash scores higher in 8 categories and Granite 3.0 8b Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GLM-4.7-Flash leads 46.5 to 27.2.
Side by side
| GLM-4.7-Flash | Granite 3.0 8b Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | IBM |
| Noometry Index | 38.8 | 31.6 |
| Released | 2026-01-19 | — |
| Weights | Open | Open |
| Context window | 200K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.06 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 21 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.7-Flash leads
GLM-4.7-Flash: 40.6 (#135), Granite 3.0 8b Instruct: 29.7 (#301)
| Benchmark | GLM-4.7-Flash | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Coding | 1383 | 1112 |
| BigCodeBench Instruct | — | 29.3% |
| BigCodeBench Complete | — | 35.4% |
Reasoning Too close to call
GLM-4.7-Flash: 20.9 (#229), Granite 3.0 8b Instruct: 20.9 (#230)
| Benchmark | GLM-4.7-Flash | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1356 | 1092 |
| Chess Puzzles | 0% | — |
Math GLM-4.7-Flash leads
GLM-4.7-Flash: 36.1 (#173), Granite 3.0 8b Instruct: 32.8 (#210)
| Benchmark | GLM-4.7-Flash | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Math | 1355 | 1143 |
| OTIS Mock AIME 2024-2025 | 58.3% | — |
Knowledge GLM-4.7-Flash leads
GLM-4.7-Flash: 35.5 (#184), Granite 3.0 8b Instruct: 29.6 (#236)
| Benchmark | GLM-4.7-Flash | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Expert | 1357 | 1087 |
| GPQA Diamond | 60.5% | — |
| Vectara Hallucination Rate | 9.3% | — |
Multilingual GLM-4.7-Flash leads
GLM-4.7-Flash: 46.5 (#158), Granite 3.0 8b Instruct: 27.2 (#276)
| Benchmark | GLM-4.7-Flash | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Non-English | 1330 | 1037 |
| LMArena Chinese | 1403 | 1063 |
| LMArena Russian | 1332 | 1060 |
| LMArena French | 1332 | — |
| LMArena German | 1337 | — |
| LMArena Korean | 1283 | — |
| LMArena Spanish | 1350 | — |
Instruction Following GLM-4.7-Flash leads
GLM-4.7-Flash: 70.1 (#167), Granite 3.0 8b Instruct: 56.0 (#276)
| Benchmark | GLM-4.7-Flash | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Instruction Following | 1327 | 1088 |
Long Context GLM-4.7-Flash leads
GLM-4.7-Flash: 40.9 (#148), Granite 3.0 8b Instruct: 34.0 (#252)
| Benchmark | GLM-4.7-Flash | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Longer Query | 1345 | 1122 |
Writing & Preference GLM-4.7-Flash leads
GLM-4.7-Flash: 47.4 (#210), Granite 3.0 8b Instruct: 31.1 (#285)
| Benchmark | GLM-4.7-Flash | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Text | 1351 | 1096 |
| LMArena Creative Writing | 1297 | 1071 |
| LMArena Multi-Turn | 1342 | 1063 |
| EQ-Bench Creative Writing | 1125 | — |
Frequently asked questions
Is GLM-4.7-Flash better than Granite 3.0 8b Instruct?
GLM-4.7-Flash is the stronger model overall, scoring 38.8 to 31.6 on the Noometry Index.
Is GLM-4.7-Flash or Granite 3.0 8b Instruct better for coding?
GLM-4.7-Flash scores higher on coding benchmarks: 40.6 versus 29.7 in the Noometry coding category.
How many benchmarks do GLM-4.7-Flash and Granite 3.0 8b Instruct share?
12 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and Granite 3.0 8b Instruct has 14.