# GLM-5.3 vs StarCoder 2 3B

> GLM-5.3 has enough public results to be ranked (#25); StarCoder 2 3B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/glm-5-3-vs-starcoder-2-3b
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. GLM-5.3 scores higher in 1 category and StarCoder 2 3B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where GLM-5.3 leads 59.0 to 32.9.

## Snapshot

| | GLM-5.3 | StarCoder 2 3B |
|---|---|---|
| Provider | Z.ai (Zhipu) | NVIDIA |
| Noometry Index | 54.6 | 35.8 |
| Rank | 25 | — |
| Context | 1M | — |
| Input $/M | $1.40 | — |
| Output $/M | $4.40 | — |
| Weights | Open | Open |

## Coding

- GLM-5.3: 59.0 (#12)
- StarCoder 2 3B: 32.9

| Benchmark | GLM-5.3 | StarCoder 2 3B |
|---|---|---|
| DeepSWE | 69% | — |
| FrontierCode | 40.1% | — |
| LMArena WebDev | 1623 | — |
| FrontierSWE | 30.2% | — |
| SciCode | 59% | — |
| WeirdML | 75.4% | — |
| LMArena Coding | 1499 | — |
| BigCodeBench Complete | — | 21.4% |
| ALE-Bench | 1,317 | — |
| HumanEval+ | — | 27.4% |

## Agentic & Tool Use

- GLM-5.3: 36.3 (#34)
- StarCoder 2 3B: —

| Benchmark | GLM-5.3 | StarCoder 2 3B |
|---|---|---|
| APEX-Agents | 56.6% | — |
| Vending-Bench 2 | 8,164 | — |

## Reasoning

- GLM-5.3: 45.2 (#42)
- StarCoder 2 3B: —

| Benchmark | GLM-5.3 | StarCoder 2 3B |
|---|---|---|
| Epoch Capabilities Index | 155.56 | 88.01 |
| NYT Connections (extended) | 74.2% | — |
| CritPt | 19.1% | — |
| Chess Puzzles | 21% | — |
| LMArena Hard Prompts | 1491 | — |
| Mystery Game Puzzles | 33% | — |
| DTBench | 87.7% | — |
| LMCA | 55.5% | — |
| Bench to the Future 3 | 0.15 | — |
| WinoGrande | — | 57.1% |

## Math

- GLM-5.3: 62.1 (#27)
- StarCoder 2 3B: —

| Benchmark | GLM-5.3 | StarCoder 2 3B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 68.8% | — |
| FrontierMath Tier 4 | 29.3% | — |
| OTIS Mock AIME 2024-2025 | 91.1% | — |
| ProofBench | 49% | — |
| LMArena Math | 1493 | — |
| GSM8K | — | 21.6% |

## Knowledge

- GLM-5.3: 58.3 (#34)
- StarCoder 2 3B: —

| Benchmark | GLM-5.3 | StarCoder 2 3B |
|---|---|---|
| GPQA Diamond | 90.9% | — |
| SimpleQA Verified | 41% | — |
| LMArena Expert | 1512 | — |
| ARC (AI2) Challenge | — | 34.2% |
| MMLU | — | 36.6% |

## Multilingual

- GLM-5.3: 55.9 (#27)
- StarCoder 2 3B: —

| Benchmark | GLM-5.3 | StarCoder 2 3B |
|---|---|---|
| LMArena Non-English | 1457 | — |
| LMArena Chinese | 1523 | — |
| LMArena French | 1499 | — |
| LMArena German | 1505 | — |
| LMArena Japanese | 1438 | — |
| LMArena Korean | 1478 | — |
| LMArena Russian | 1460 | — |
| LMArena Spanish | 1444 | — |

## Instruction Following

- GLM-5.3: 77.8 (#15)
- StarCoder 2 3B: —

| Benchmark | GLM-5.3 | StarCoder 2 3B |
|---|---|---|
| LMArena Instruction Following | 1481 | — |

## Long Context

- GLM-5.3: 45.5 (#32)
- StarCoder 2 3B: —

| Benchmark | GLM-5.3 | StarCoder 2 3B |
|---|---|---|
| LMArena Longer Query | 1485 | — |

## Writing & Preference

- GLM-5.3: 75.9 (#6)
- StarCoder 2 3B: —

| Benchmark | GLM-5.3 | StarCoder 2 3B |
|---|---|---|
| LMArena Text | 1473 | — |
| LMArena Creative Writing | 1459 | — |
| EQ-Bench Creative Writing | 2075 | — |
| LMArena Multi-Turn | 1473 | — |

## FAQ

### Is GLM-5.3 better than StarCoder 2 3B?

GLM-5.3 has enough public results to be ranked (#25); StarCoder 2 3B does not yet, so treat this comparison as directional.

### Is GLM-5.3 or StarCoder 2 3B better for coding?

GLM-5.3 scores higher on coding benchmarks: 59.0 versus 32.9 in the Noometry coding category.

### How many benchmarks do GLM-5.3 and StarCoder 2 3B share?

1 benchmark has published results for both models. GLM-5.3 has 41 scored results on Noometry and StarCoder 2 3B has 7.