Model comparison
GLM-5 vs Granite 3.1 2b Instruct
GLM-5 is the stronger model overall, scoring 46.1 to 33.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. GLM-5 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-5 leads 66.0 to 34.1.
Side by side
| GLM-5 | Granite 3.1 2b Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | IBM |
| Noometry Index | 46.1 | 33.2 |
| Released | 2026-02-11 | — |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 45 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), Granite 3.1 2b Instruct: 33.4 (#257)
| Benchmark | GLM-5 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Coding | 1461 | 1149 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| WeirdML | 48.2% | — |
| ALE-Bench | 765.62 | — |
Agentic & Tool Use Not comparable
GLM-5: 31.1 (#71), Granite 3.1 2b Instruct: —
| Benchmark | GLM-5 | Granite 3.1 2b Instruct |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| Vending-Bench 2 | 4,432 | — |
Reasoning GLM-5 leads
GLM-5: 27.6 (#116), Granite 3.1 2b Instruct: 22.0 (#209)
| Benchmark | GLM-5 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1138 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 53.2% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 74.8% | — |
| ARC-AGI-1 | 44.7% | — |
| Chess Puzzles | 10% | — |
| Epoch Capabilities Index | 145.83 | — |
| ForecastBench | 61 | — |
Math GLM-5 leads
GLM-5: 46.4 (#71), Granite 3.1 2b Instruct: 33.1 (#206)
| Benchmark | GLM-5 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Math | 1440 | 1159 |
| MathArena Final-Answer Competitions | 65.7% | — |
| OTIS Mock AIME 2024-2025 | 80% | — |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-5 leads
GLM-5: 52.3 (#64), Granite 3.1 2b Instruct: 30.8 (#224)
| Benchmark | GLM-5 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Expert | 1454 | 1131 |
| GPQA Diamond | 87.8% | — |
| Vectara Hallucination Rate | 10.1% | — |
Multilingual GLM-5 leads
GLM-5: 53.7 (#58), Granite 3.1 2b Instruct: 29.1 (#269)
| Benchmark | GLM-5 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Non-English | 1430 | 1068 |
| LMArena Chinese | 1511 | 1139 |
| LMArena Russian | 1436 | 1063 |
| LMArena French | 1455 | — |
| LMArena German | 1445 | — |
| LMArena Japanese | 1416 | — |
| LMArena Korean | 1423 | — |
| LMArena Spanish | 1454 | — |
Instruction Following GLM-5 leads
GLM-5: 75.2 (#67), Granite 3.1 2b Instruct: 57.7 (#264)
| Benchmark | GLM-5 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Instruction Following | 1428 | 1116 |
Long Context GLM-5 leads
GLM-5: 44.7 (#60), Granite 3.1 2b Instruct: 35.0 (#244)
| Benchmark | GLM-5 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Longer Query | 1446 | 1155 |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.0 (#38), Granite 3.1 2b Instruct: 34.1 (#274)
| Benchmark | GLM-5 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Text | 1446 | 1127 |
| LMArena Creative Writing | 1439 | 1116 |
| LMArena Multi-Turn | 1456 | 1099 |
| EQ-Bench Creative Writing | 1601 | — |
Frequently asked questions
Is GLM-5 better than Granite 3.1 2b Instruct?
GLM-5 is the stronger model overall, scoring 46.1 to 33.2 on the Noometry Index.
Is GLM-5 or Granite 3.1 2b Instruct better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 33.4 in the Noometry coding category.
How many benchmarks do GLM-5 and Granite 3.1 2b Instruct share?
12 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Granite 3.1 2b Instruct has 12.