# GLM-4.5 vs Nemotron 3 Super

> GLM-4.5 is the stronger model overall, scoring 41.4 to 39.6 on the Noometry Index. Nemotron 3 Super costs 5.8× less per token, which makes it the better buy when GLM-4.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-4-5-vs-nemotron-3-super
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. GLM-4.5 scores higher in 5 categories and Nemotron 3 Super in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-4.5 leads 27.7 to 17.9.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $0.60 / $2.20 for GLM-4.5.
- Nemotron 3 Super accepts more context: 262K tokens versus 131K.

## Snapshot

| | GLM-4.5 | Nemotron 3 Super |
|---|---|---|
| Provider | Z.ai (Zhipu) | NVIDIA |
| Noometry Index | 41.4 | 39.6 |
| Rank | 125 | 147 |
| Context | 131K | 262K |
| Input $/M | $0.60 | $0.08 |
| Output $/M | $2.20 | $0.45 |
| Weights | Open | Open |

## Coding

- GLM-4.5: 41.1 (#121)
- Nemotron 3 Super: 38.9 (#153)

| Benchmark | GLM-4.5 | Nemotron 3 Super |
|---|---|---|
| WeirdML | 40.6% | 38% |
| LMArena Coding | 1434 | 1403 |
| ALE-Bench | 344.82 | 213.9 |
| SWE-bench Verified (bash only) | 54.2% | — |
| SciCode | — | 36% |
| AlgoTune | 1.52 | — |

## Reasoning

- GLM-4.5: 27.7 (#99)
- Nemotron 3 Super: 17.9 (#274)

| Benchmark | GLM-4.5 | Nemotron 3 Super |
|---|---|---|
| LMArena Hard Prompts | 1430 | 1386 |
| Kagi LLM Benchmark | 57.9% | — |
| NYT Connections (extended) | — | 15.4% |
| CritPt | — | 3.1% |

## Math

- GLM-4.5: 36.3 (#119)
- Nemotron 3 Super: 37.6 (#95)

| Benchmark | GLM-4.5 | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1427 | 1381 |
| MathArena Final-Answer Competitions | — | 60.4% |

## Knowledge

- GLM-4.5: 35.5 (#172)
- Nemotron 3 Super: 38.2 (#136)

| Benchmark | GLM-4.5 | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1433 | 1397 |
| Humanity's Last Exam | 8.3% | — |
| Confabulations | 11.3% | — |

## Multilingual

- GLM-4.5: 53.0 (#74)
- Nemotron 3 Super: 48.6 (#139)

| Benchmark | GLM-4.5 | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1417 | 1356 |
| LMArena Chinese | 1465 | 1430 |
| LMArena French | 1423 | 1404 |
| LMArena German | 1406 | 1341 |
| LMArena Russian | 1414 | 1336 |
| LMArena Spanish | 1454 | 1417 |
| LMArena Japanese | 1416 | — |
| LMArena Korean | 1382 | — |

## Instruction Following

- GLM-4.5: 74.3 (#100)
- Nemotron 3 Super: 71.4 (#149)

| Benchmark | GLM-4.5 | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1405 | 1347 |

## Long Context

- GLM-4.5: 38.2 (#196)
- Nemotron 3 Super: 41.5 (#134)

| Benchmark | GLM-4.5 | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1413 | 1362 |
| Fiction.LiveBench | 58.3% | — |

## Writing & Preference

- GLM-4.5: 57.7 (#121)
- Nemotron 3 Super: 56.1 (#135)

| Benchmark | GLM-4.5 | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1430 | 1378 |
| LMArena Creative Writing | 1395 | 1317 |
| LMArena Multi-Turn | 1415 | 1369 |
| Short-Story Creative Writing | 73.4% | — |
| EQ-Bench Creative Writing | 1343 | — |

## FAQ

### Is GLM-4.5 better than Nemotron 3 Super?

GLM-4.5 is the stronger model overall, scoring 41.4 to 39.6 on the Noometry Index. Nemotron 3 Super costs 5.8× less per token, which makes it the better buy when GLM-4.5's lead doesn't matter for your workload.

### Which is cheaper, GLM-4.5 or Nemotron 3 Super?

Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; GLM-4.5 lists at $0.60 and $2.20.

### Is GLM-4.5 or Nemotron 3 Super better for coding?

GLM-4.5 scores higher on coding benchmarks: 41.1 versus 38.9 in the Noometry coding category.

### Which has the bigger context window?

Nemotron 3 Super does, with 262K tokens against 131K.

### How many benchmarks do GLM-4.5 and Nemotron 3 Super share?

17 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Nemotron 3 Super has 21.