Model comparison
Gemma 4 31B IT vs GLM-4.6
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 41.4 on the Noometry Index.
Last verified . 21 shared benchmarks.
GoogleSummary
- They share 21 benchmarks with published results for both. Gemma 4 31B IT scores higher in 6 categories and GLM-4.6 in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 31B IT leads 43.2 to 39.1.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 63.5% for Gemma 4 31B IT and 47.4% for GLM-4.6.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- Gemma 4 31B IT accepts more context: 262K tokens versus 205K.
Side by side
| Gemma 4 31B IT | GLM-4.6 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 43.5 | 41.4 |
| Released | 2026-04-02 | 2025-09-30 |
| Weights | Open | Open |
| Context window | 262K | 205K |
| Max output | 33K | 131K |
| Input $ / M tokens | $0.09 | $0.60 |
| Output $ / M tokens | $0.34 | $2.20 |
| Results tracked | 35 | 29 |
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: 42.3 (#108), GLM-4.6: 40.1 (#148)
| Benchmark | Gemma 4 31B IT | GLM-4.6 |
|---|---|---|
| LMArena WebDev | 1366 | 1340 |
| SciCode | 43.4% | 38.4% |
| LMArena Coding | 1459 | 1449 |
| ALE-Bench | 925.5 | 340.82 |
| SWE-bench Verified (bash only) | — | 55.4% |
| WeirdML | 52.3% | — |
Agentic & Tool Use Not comparable
Gemma 4 31B IT: —, GLM-4.6: 32.3 (#66)
| Benchmark | Gemma 4 31B IT | GLM-4.6 |
|---|---|---|
| Terminal-Bench | — | 24.5% |
| Berkeley Function Calling Leaderboard | — | 72.4% |
Reasoning Gemma 4 31B IT leads
Gemma 4 31B IT: 27.2 (#122), GLM-4.6: 23.7 (#172)
| Benchmark | Gemma 4 31B IT | GLM-4.6 |
|---|---|---|
| Kagi LLM Benchmark | 63.5% | 47.4% |
| CritPt | 1.4% | 1.1% |
| LMArena Hard Prompts | 1448 | 1440 |
| NYT Connections (extended) | 70.6% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| DTBench | 82.7% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| Epoch Capabilities Index | 142.74 | — |
Math Gemma 4 31B IT leads
Gemma 4 31B IT: 43.2 (#81), GLM-4.6: 39.1 (#111)
| Benchmark | Gemma 4 31B IT | GLM-4.6 |
|---|---|---|
| LMArena Math | 1465 | 1432 |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GLM-4.6 leads
Gemma 4 31B IT: 37.9 (#151), GLM-4.6: 40.2 (#124)
| Benchmark | Gemma 4 31B IT | GLM-4.6 |
|---|---|---|
| Vectara Hallucination Rate | 7.4% | 9.5% |
| LMArena Expert | 1465 | 1431 |
| GPQA Diamond | 75.8% | — |
| SimpleQA Verified | 10.4% | — |
Multimodal Not comparable
Gemma 4 31B IT: 41.6 (#34), GLM-4.6: —
| Benchmark | Gemma 4 31B IT | GLM-4.6 |
|---|---|---|
| LMArena Vision | 1277 | — |
| LMArena Document | 1425 | — |
Multilingual Too close to call
Gemma 4 31B IT: 53.8 (#57), GLM-4.6: 53.5 (#66)
| Benchmark | Gemma 4 31B IT | GLM-4.6 |
|---|---|---|
| LMArena Non-English | 1431 | 1426 |
| LMArena Chinese | 1476 | 1499 |
| LMArena French | 1435 | 1459 |
| LMArena Russian | 1460 | 1419 |
| LMArena Spanish | 1444 | 1436 |
| LMArena German | — | 1447 |
| LMArena Japanese | — | 1393 |
| LMArena Korean | — | 1400 |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.5 (#61), GLM-4.6: 74.3 (#98)
| Benchmark | Gemma 4 31B IT | GLM-4.6 |
|---|---|---|
| LMArena Instruction Following | 1433 | 1410 |
Long Context Too close to call
Gemma 4 31B IT: 44.2 (#71), GLM-4.6: 43.4 (#94)
| Benchmark | Gemma 4 31B IT | GLM-4.6 |
|---|---|---|
| LMArena Longer Query | 1446 | 1422 |
Writing & Preference Too close to call
Gemma 4 31B IT: 60.5 (#96), GLM-4.6: 61.1 (#90)
| Benchmark | Gemma 4 31B IT | GLM-4.6 |
|---|---|---|
| LMArena Text | 1443 | 1440 |
| LMArena Creative Writing | 1415 | 1411 |
| EQ-Bench Creative Writing | 1368 | 1411 |
| LMArena Multi-Turn | 1452 | 1427 |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than GLM-4.6?
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 41.4 on the Noometry Index.
Which is cheaper, Gemma 4 31B IT or GLM-4.6?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.
Is Gemma 4 31B IT or GLM-4.6 better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
Gemma 4 31B IT does, with 262K tokens against 205K.
How many benchmarks do Gemma 4 31B IT and GLM-4.6 share?
21 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and GLM-4.6 has 29.