Model comparison
Gemma 4 26B A4B IT vs GLM-5
GLM-5 is the stronger model overall, scoring 46.1 to 43.5 on the Noometry Index. Gemma 4 26B A4B IT costs 15× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
GoogleSummary
- They share 23 benchmarks with published results for both. Gemma 4 26B A4B IT scores higher in 1 category and GLM-5 in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where GLM-5 leads 49.0 to 39.0.
- The biggest single-benchmark swing is GPQA Diamond: 73.2% for Gemma 4 26B A4B IT and 87.8% for GLM-5.
- Gemma 4 26B A4B IT is cheaper at $0.0675 / $0.23 per million input/output tokens, against $1 / $3.20 for GLM-5.
- Gemma 4 26B A4B IT accepts more context: 262K tokens versus 205K.
Side by side
| Gemma 4 26B A4B 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 | $0.0675 | $1 |
| Output $ / M tokens | $0.23 | $3.20 |
| Results tracked | 28 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
Gemma 4 26B A4B IT: 39.0 (#164), GLM-5: 49.0 (#52)
| Benchmark | Gemma 4 26B A4B IT | GLM-5 |
|---|---|---|
| LMArena WebDev | 1359 | 1434 |
| WeirdML | 35.2% | 48.2% |
| LMArena Coding | 1447 | 1461 |
| ALE-Bench | 927.17 | 765.62 |
| SWE-bench Verified | — | 72.1% |
| SWE-bench Verified (bash only) | — | 72.8% |
| SWE-bench Multilingual | — | 69.7% |
| SciCode | 40% | — |
Agentic & Tool Use Not comparable
Gemma 4 26B A4B IT: —, GLM-5: 31.1 (#71)
| Benchmark | Gemma 4 26B A4B 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 GLM-5 leads
Gemma 4 26B A4B IT: 21.8 (#213), GLM-5: 27.6 (#116)
| Benchmark | Gemma 4 26B A4B IT | GLM-5 |
|---|---|---|
| Chess Puzzles | 6% | 10% |
| LMArena Hard Prompts | 1439 | 1452 |
| Epoch Capabilities Index | 141.85 | 145.83 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | — | 53.2% |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 74.8% |
| ARC-AGI-1 | — | 44.7% |
| CritPt | 0% | — |
| DTBench | 74.9% | — |
| LMCA | 29.7% | — |
| ForecastBench | — | 61 |
Math Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 47.6 (#67), GLM-5: 46.4 (#71)
| Benchmark | Gemma 4 26B A4B IT | GLM-5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 82.2% | 80% |
| LMArena Math | 1470 | 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 26B A4B IT: 45.7 (#85), GLM-5: 52.3 (#64)
| Benchmark | Gemma 4 26B A4B IT | GLM-5 |
|---|---|---|
| GPQA Diamond | 73.2% | 87.8% |
| Vectara Hallucination Rate | 5.2% | 10.1% |
| LMArena Expert | 1447 | 1454 |
Multimodal Not comparable
Gemma 4 26B A4B IT: 40.6 (#46), GLM-5: —
| Benchmark | Gemma 4 26B A4B IT | GLM-5 |
|---|---|---|
| LMArena Vision | 1260 | — |
Multilingual Too close to call
Gemma 4 26B A4B IT: 53.1 (#71), GLM-5: 53.7 (#58)
| Benchmark | Gemma 4 26B A4B IT | GLM-5 |
|---|---|---|
| LMArena Non-English | 1421 | 1430 |
| LMArena Chinese | 1495 | 1511 |
| LMArena French | 1460 | 1455 |
| LMArena Russian | 1434 | 1436 |
| LMArena Spanish | 1417 | 1454 |
| LMArena German | — | 1445 |
| LMArena Japanese | — | 1416 |
| LMArena Korean | — | 1423 |
Instruction Following Too close to call
Gemma 4 26B A4B IT: 74.8 (#82), GLM-5: 75.2 (#67)
| Benchmark | Gemma 4 26B A4B IT | GLM-5 |
|---|---|---|
| LMArena Instruction Following | 1420 | 1428 |
Long Context GLM-5 leads
Gemma 4 26B A4B IT: 43.6 (#91), GLM-5: 44.7 (#60)
| Benchmark | Gemma 4 26B A4B IT | GLM-5 |
|---|---|---|
| LMArena Longer Query | 1428 | 1446 |
| CL-bench | — | 18.7% |
Writing & Preference GLM-5 leads
Gemma 4 26B A4B IT: 58.6 (#115), GLM-5: 66.0 (#38)
| Benchmark | Gemma 4 26B A4B IT | GLM-5 |
|---|---|---|
| LMArena Text | 1434 | 1446 |
| LMArena Creative Writing | 1402 | 1439 |
| EQ-Bench Creative Writing | 1305 | 1601 |
| LMArena Multi-Turn | 1441 | 1456 |
Frequently asked questions
Is Gemma 4 26B A4B IT better than GLM-5?
GLM-5 is the stronger model overall, scoring 46.1 to 43.5 on the Noometry Index. Gemma 4 26B A4B IT costs 15× 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 26B A4B IT or GLM-5?
Gemma 4 26B A4B IT is cheaper. It lists at $0.0675 per million input tokens and $0.23 per million output tokens; GLM-5 lists at $1 and $3.20.
Is Gemma 4 26B A4B IT or GLM-5 better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 39.0 in the Noometry coding category.
Which has the bigger context window?
Gemma 4 26B A4B IT does, with 262K tokens against 205K.
How many benchmarks do Gemma 4 26B A4B IT and GLM-5 share?
23 benchmarks have published results for both models. Gemma 4 26B A4B IT has 28 scored results on Noometry and GLM-5 has 45.