Model comparison
Gemma 4 31B IT vs GLM-4.5-Air
Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 38.7 on the Noometry Index.
Last verified . 16 shared benchmarks.
GoogleSummary
- They share 16 benchmarks with published results for both. Gemma 4 31B IT scores higher in 8 categories and GLM-4.5-Air in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 31B IT leads 41.3 to 33.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 63.5% for Gemma 4 31B IT and 43% for GLM-4.5-Air.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.20 / $1.10 for GLM-4.5-Air.
- Gemma 4 31B IT accepts more context: 262K tokens versus 131K.
Side by side
| Gemma 4 31B IT | GLM-4.5-Air | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 43.2 | 38.7 |
| Released | 2026-04-02 | 2025-07-20 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 33K | 98K |
| Input $ / M tokens | $0.09 | $0.20 |
| Output $ / M tokens | $0.34 | $1.10 |
| Results tracked | 35 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Gemma 4 31B IT: 41.9 (#98), GLM-4.5-Air: 34.5 (#225)
| Benchmark | Gemma 4 31B IT | GLM-4.5-Air |
|---|---|---|
| LMArena Coding | 1459 | 1397 |
| LMArena WebDev | 1364 | — |
| SciCode | 43.4% | — |
| GSO | — | 2.9% |
| WeirdML | 52.3% | — |
| ALE-Bench | 925.5 | — |
Reasoning Gemma 4 31B IT leads
Gemma 4 31B IT: 26.4 (#119), GLM-4.5-Air: 23.3 (#166)
| Benchmark | Gemma 4 31B IT | GLM-4.5-Air |
|---|---|---|
| Kagi LLM Benchmark | 63.5% | 43% |
| LMArena Hard Prompts | 1448 | 1379 |
| NYT Connections (extended) | 70.6% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| DTBench | 82.7% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| Epoch Capabilities Index | 142.74 | — |
| ForecastBench | — | 59.2 |
Math Gemma 4 31B IT leads
Gemma 4 31B IT: 41.3 (#72), GLM-4.5-Air: 33.8 (#166)
| Benchmark | Gemma 4 31B IT | GLM-4.5-Air |
|---|---|---|
| LMArena Math | 1464 | 1396 |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
| Omni-MATH | — | 39.1% |
Knowledge Gemma 4 31B IT leads
Gemma 4 31B IT: 37.9 (#141), GLM-4.5-Air: 34.6 (#184)
| Benchmark | Gemma 4 31B IT | GLM-4.5-Air |
|---|---|---|
| Vectara Hallucination Rate | 7.4% | 9.3% |
| LMArena Expert | 1465 | 1370 |
| GPQA Diamond | 75.8% | — |
| Humanity's Last Exam | — | 8.1% |
| SimpleQA Verified | 10.4% | — |
| MMLU-Pro | — | 76.2% |
| GPQA (HELM) | — | 59.4% |
Multimodal Not comparable
Gemma 4 31B IT: 41.0 (#32), GLM-4.5-Air: —
| Benchmark | Gemma 4 31B IT | GLM-4.5-Air |
|---|---|---|
| LMArena Vision | 1278 | — |
| LMArena Document | 1425 | — |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 54.0 (#52), GLM-4.5-Air: 49.4 (#130)
| Benchmark | Gemma 4 31B IT | GLM-4.5-Air |
|---|---|---|
| LMArena Non-English | 1431 | 1366 |
| LMArena Chinese | 1478 | 1427 |
| LMArena French | 1436 | 1399 |
| LMArena Russian | 1462 | 1373 |
| LMArena Spanish | 1443 | 1385 |
| LMArena German | — | 1376 |
| LMArena Japanese | — | 1348 |
| LMArena Korean | — | 1306 |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.6 (#58), GLM-4.5-Air: 69.8 (#165)
| Benchmark | Gemma 4 31B IT | GLM-4.5-Air |
|---|---|---|
| LMArena Instruction Following | 1433 | 1353 |
| IFEval | — | 81.2% |
Long Context Gemma 4 31B IT leads
Gemma 4 31B IT: 44.2 (#67), GLM-4.5-Air: 41.6 (#130)
| Benchmark | Gemma 4 31B IT | GLM-4.5-Air |
|---|---|---|
| LMArena Longer Query | 1446 | 1367 |
Writing & Preference Gemma 4 31B IT leads
Gemma 4 31B IT: 60.7 (#92), GLM-4.5-Air: 56.1 (#134)
| Benchmark | Gemma 4 31B IT | GLM-4.5-Air |
|---|---|---|
| LMArena Text | 1443 | 1384 |
| LMArena Creative Writing | 1416 | 1343 |
| LMArena Multi-Turn | 1452 | 1371 |
| EQ-Bench Creative Writing | 1368 | — |
| WildBench | — | 78.9% |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than GLM-4.5-Air?
Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 38.7 on the Noometry Index.
Which is cheaper, Gemma 4 31B IT or GLM-4.5-Air?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; GLM-4.5-Air lists at $0.20 and $1.10.
Is Gemma 4 31B IT or GLM-4.5-Air better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 41.9 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
Gemma 4 31B IT does, with 262K tokens against 131K.
How many benchmarks do Gemma 4 31B IT and GLM-4.5-Air share?
16 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and GLM-4.5-Air has 27.