Model comparison
GLM-4.5 vs Nova 2 Lite
GLM-4.5 is the stronger model overall, scoring 42.0 to 39.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. GLM-4.5 scores higher in 6 categories and Nova 2 Lite in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nova 2 Lite leads 43.0 to 35.9.
- Nova 2 Lite is cheaper at $0.30 / $2.50 per million input/output tokens, against $0.60 / $2.20 for GLM-4.5.
- Nova 2 Lite accepts more context: 1M tokens versus 131K.
- GLM-4.5 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.5 | Nova 2 Lite | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Amazon |
| Noometry Index | 42.0 | 39.7 |
| Released | 2025-07-27 | 2025-12-01 |
| Weights | Open | Proprietary |
| Context window | 131K | 1M |
| Max output | 98K | 64K |
| Input $ / M tokens | $0.60 | $0.30 |
| Output $ / M tokens | $2.20 | $2.50 |
| Results tracked | 27 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-4.5: 41.4 (#125), Nova 2 Lite: 40.7 (#134)
| Benchmark | GLM-4.5 | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1434 | 1385 |
| SWE-bench Verified (bash only) | 54.2% | — |
| WeirdML | 40.6% | — |
| ALE-Bench | 344.82 | — |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Not comparable
GLM-4.5: —, Nova 2 Lite: 24.1 (#121)
| Benchmark | GLM-4.5 | Nova 2 Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.1% |
Reasoning GLM-4.5 leads
GLM-4.5: 28.6 (#100), Nova 2 Lite: 27.5 (#118)
| Benchmark | GLM-4.5 | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1429 | 1364 |
| Kagi LLM Benchmark | 57.9% | — |
Math GLM-4.5 leads
GLM-4.5: 39.0 (#116), Nova 2 Lite: 37.5 (#156)
| Benchmark | GLM-4.5 | Nova 2 Lite |
|---|---|---|
| LMArena Math | 1427 | 1359 |
Knowledge Nova 2 Lite leads
GLM-4.5: 35.9 (#179), Nova 2 Lite: 43.0 (#94)
| Benchmark | GLM-4.5 | Nova 2 Lite |
|---|---|---|
| LMArena Expert | 1433 | 1358 |
| Humanity's Last Exam | 8.3% | — |
| Confabulations | 11.3% | — |
| Vectara Hallucination Rate | — | 5.1% |
Multilingual GLM-4.5 leads
GLM-4.5: 52.8 (#77), Nova 2 Lite: 47.1 (#153)
| Benchmark | GLM-4.5 | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1417 | 1337 |
| LMArena Chinese | 1465 | 1364 |
| LMArena French | 1418 | 1381 |
| LMArena German | 1407 | 1343 |
| LMArena Japanese | 1415 | 1271 |
| LMArena Korean | 1380 | 1284 |
| LMArena Russian | 1414 | 1343 |
| LMArena Spanish | 1454 | 1373 |
Instruction Following GLM-4.5 leads
GLM-4.5: 74.1 (#104), Nova 2 Lite: 70.5 (#161)
| Benchmark | GLM-4.5 | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1404 | 1335 |
Long Context Nova 2 Lite leads
GLM-4.5: 38.2 (#201), Nova 2 Lite: 40.6 (#150)
| Benchmark | GLM-4.5 | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1412 | 1335 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference GLM-4.5 leads
GLM-4.5: 57.5 (#127), Nova 2 Lite: 53.9 (#154)
| Benchmark | GLM-4.5 | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1430 | 1362 |
| LMArena Creative Writing | 1395 | 1291 |
| LMArena Multi-Turn | 1415 | 1338 |
| Short-Story Creative Writing | 73.4% | — |
| EQ-Bench Creative Writing | 1343 | — |
Frequently asked questions
Is GLM-4.5 better than Nova 2 Lite?
GLM-4.5 is the stronger model overall, scoring 42.0 to 39.7 on the Noometry Index.
Which is cheaper, GLM-4.5 or Nova 2 Lite?
Nova 2 Lite is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; GLM-4.5 lists at $0.60 and $2.20.
Is GLM-4.5 or Nova 2 Lite better for coding?
They score almost the same on coding (41.4 vs 40.7); test both on your own repository before choosing.
Which has the bigger context window?
Nova 2 Lite does, with 1M tokens against 131K.
How many benchmarks do GLM-4.5 and Nova 2 Lite share?
17 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Nova 2 Lite has 19.