Model comparison
Gemma 4 31B IT vs GLM-5
GLM-5 is the stronger model overall, scoring 46.1 to 43.5 on the Noometry Index. Gemma 4 31B IT costs 10× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
GoogleSummary
- They share 25 benchmarks with published results for both. Gemma 4 31B IT scores higher in 2 categories and GLM-5 in 6 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5 leads 52.3 to 37.9.
- The biggest single-benchmark swing is GPQA Diamond: 75.8% for Gemma 4 31B IT and 87.8% for GLM-5.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $1 / $3.20 for GLM-5.
- Gemma 4 31B IT accepts more context: 262K tokens versus 205K.
Side by side
| Gemma 4 31B IT | GLM-5 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | |
| Noometry Index | 43.5 | 46.1 |
| Released | 2026-04-02 | 2026-02-11 |
| Weights | Open | Open |
| Context window | 262K | 205K |
| Max output | 33K | 131K |
| Input $ / M tokens | $0.09 | $1 |
| Output $ / M tokens | $0.34 | $3.20 |
| Results tracked | 35 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
Gemma 4 31B IT: 42.3 (#108), GLM-5: 49.0 (#52)
| Benchmark | Gemma 4 31B IT | GLM-5 |
|---|---|---|
| LMArena WebDev | 1366 | 1434 |
| WeirdML | 52.3% | 48.2% |
| LMArena Coding | 1459 | 1461 |
| ALE-Bench | 925.5 | 765.62 |
| SWE-bench Verified | — | 72.1% |
| SWE-bench Verified (bash only) | — | 72.8% |
| SWE-bench Multilingual | — | 69.7% |
| SciCode | 43.4% | — |
Agentic & Tool Use Not comparable
Gemma 4 31B IT: —, GLM-5: 31.1 (#71)
| Benchmark | Gemma 4 31B IT | GLM-5 |
|---|---|---|
| Terminal-Bench | — | 52.4% |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 73.7% |
| τ²-bench Telecom | — | 86.8% |
| Vending-Bench 2 | — | 4,432 |
Reasoning Too close to call
Gemma 4 31B IT: 27.2 (#122), GLM-5: 27.6 (#116)
| Benchmark | Gemma 4 31B IT | GLM-5 |
|---|---|---|
| Kagi LLM Benchmark | 63.5% | 75% |
| NYT Connections (extended) | 70.6% | 74.8% |
| Chess Puzzles | 5% | 10% |
| LMArena Hard Prompts | 1448 | 1452 |
| Epoch Capabilities Index | 142.74 | 145.83 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | — | 53.2% |
| ARC-AGI-1 | — | 44.7% |
| CritPt | 1.4% | — |
| Thematic Generalization | 53% | — |
| DTBench | 82.7% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| ForecastBench | — | 61 |
Math GLM-5 leads
Gemma 4 31B IT: 43.2 (#81), GLM-5: 46.4 (#71)
| Benchmark | Gemma 4 31B IT | GLM-5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 80% |
| LMArena Math | 1465 | 1440 |
| MathArena Final-Answer Competitions | — | 65.7% |
| FrontierMath (Feb 2025 set) | — | 16.4% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GLM-5 leads
Gemma 4 31B IT: 37.9 (#151), GLM-5: 52.3 (#64)
| Benchmark | Gemma 4 31B IT | GLM-5 |
|---|---|---|
| GPQA Diamond | 75.8% | 87.8% |
| Vectara Hallucination Rate | 7.4% | 10.1% |
| LMArena Expert | 1465 | 1454 |
| SimpleQA Verified | 10.4% | — |
Multimodal Not comparable
Gemma 4 31B IT: 41.6 (#34), GLM-5: —
| Benchmark | Gemma 4 31B IT | GLM-5 |
|---|---|---|
| LMArena Vision | 1277 | — |
| LMArena Document | 1425 | — |
Multilingual Too close to call
Gemma 4 31B IT: 53.8 (#57), GLM-5: 53.7 (#58)
| Benchmark | Gemma 4 31B IT | GLM-5 |
|---|---|---|
| LMArena Non-English | 1431 | 1430 |
| LMArena Chinese | 1476 | 1511 |
| LMArena French | 1435 | 1455 |
| LMArena Russian | 1460 | 1436 |
| LMArena Spanish | 1444 | 1454 |
| LMArena German | — | 1445 |
| LMArena Japanese | — | 1416 |
| LMArena Korean | — | 1423 |
Instruction Following Too close to call
Gemma 4 31B IT: 75.5 (#61), GLM-5: 75.2 (#67)
| Benchmark | Gemma 4 31B IT | GLM-5 |
|---|---|---|
| LMArena Instruction Following | 1433 | 1428 |
Long Context Too close to call
Gemma 4 31B IT: 44.2 (#71), GLM-5: 44.7 (#60)
| Benchmark | Gemma 4 31B IT | GLM-5 |
|---|---|---|
| LMArena Longer Query | 1446 | 1446 |
| CL-bench | — | 18.7% |
Writing & Preference GLM-5 leads
Gemma 4 31B IT: 60.5 (#96), GLM-5: 66.0 (#38)
| Benchmark | Gemma 4 31B IT | GLM-5 |
|---|---|---|
| LMArena Text | 1443 | 1446 |
| LMArena Creative Writing | 1415 | 1439 |
| EQ-Bench Creative Writing | 1368 | 1601 |
| LMArena Multi-Turn | 1452 | 1456 |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than GLM-5?
GLM-5 is the stronger model overall, scoring 46.1 to 43.5 on the Noometry Index. Gemma 4 31B IT costs 10× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.
Which is cheaper, Gemma 4 31B IT or GLM-5?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; GLM-5 lists at $1 and $3.20.
Is Gemma 4 31B IT or GLM-5 better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 42.3 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-5 share?
25 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and GLM-5 has 45.