Model comparison
GLM-5 vs Qwen2.5 32B Instruct
GLM-5 is the stronger model overall, scoring 46.1 to 30.1 on the Noometry Index.
Last verified . 4 shared benchmarks.
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. GLM-5 scores higher in 4 categories and Qwen2.5 32B Instruct in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5 leads 46.4 to 16.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 80% for GLM-5 and 7.4% for Qwen2.5 32B Instruct.
- Qwen2.5 32B Instruct is cheaper at $0.70 / $2.80 per million input/output tokens, against $1 / $3.20 for GLM-5.
- GLM-5 accepts more context: 205K tokens versus 131K.
Side by side
| GLM-5 | Qwen2.5 32B Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 46.1 | 30.1 |
| Released | 2026-02-11 | 2024-09 |
| Weights | Open | Open |
| Context window | 205K | 131K |
| Max output | 131K | 8K |
| Input $ / M tokens | $1 | $0.70 |
| Output $ / M tokens | $3.20 | $2.80 |
| Results tracked | 45 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), Qwen2.5 32B Instruct: 38.7 (#169)
| Benchmark | GLM-5 | Qwen2.5 32B Instruct |
|---|---|---|
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| WeirdML | 48.2% | — |
| BigCodeBench Instruct | — | 45% |
| LMArena Coding | 1461 | — |
| BigCodeBench Complete | — | 52.3% |
| ALE-Bench | 765.62 | — |
Agentic & Tool Use Not comparable
GLM-5: 31.1 (#71), Qwen2.5 32B Instruct: —
| Benchmark | GLM-5 | Qwen2.5 32B Instruct |
|---|---|---|
| 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
GLM-5: 27.6 (#116), Qwen2.5 32B Instruct: 19.2 (#266)
| Benchmark | GLM-5 | Qwen2.5 32B Instruct |
|---|---|---|
| Chess Puzzles | 10% | 0% |
| Epoch Capabilities Index | 145.83 | 128.52 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 53.2% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 74.8% | — |
| ARC-AGI-1 | 44.7% | — |
| LMArena Hard Prompts | 1452 | — |
| ForecastBench | 61 | — |
Math GLM-5 leads
GLM-5: 46.4 (#71), Qwen2.5 32B Instruct: 16.2 (#296)
| Benchmark | GLM-5 | Qwen2.5 32B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 7.4% |
| MathArena Final-Answer Competitions | 65.7% | — |
| LMArena Math | 1440 | — |
| MATH Level 5 | — | 56.1% |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-5 leads
GLM-5: 52.3 (#64), Qwen2.5 32B Instruct: 24.9 (#266)
| Benchmark | GLM-5 | Qwen2.5 32B Instruct |
|---|---|---|
| GPQA Diamond | 87.8% | 46.1% |
| Vectara Hallucination Rate | 10.1% | — |
| LMArena Expert | 1454 | — |
Multilingual Not comparable
GLM-5: 53.7 (#58), Qwen2.5 32B Instruct: —
| Benchmark | GLM-5 | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Non-English | 1430 | — |
| LMArena Chinese | 1511 | — |
| LMArena French | 1455 | — |
| LMArena German | 1445 | — |
| LMArena Japanese | 1416 | — |
| LMArena Korean | 1423 | — |
| LMArena Russian | 1436 | — |
| LMArena Spanish | 1454 | — |
Instruction Following Not comparable
GLM-5: 75.2 (#67), Qwen2.5 32B Instruct: —
| Benchmark | GLM-5 | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Instruction Following | 1428 | — |
Long Context Not comparable
GLM-5: 44.7 (#60), Qwen2.5 32B Instruct: —
| Benchmark | GLM-5 | Qwen2.5 32B Instruct |
|---|---|---|
| CL-bench | 18.7% | — |
| LMArena Longer Query | 1446 | — |
Writing & Preference Not comparable
GLM-5: 66.0 (#38), Qwen2.5 32B Instruct: —
| Benchmark | GLM-5 | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Text | 1446 | — |
| LMArena Creative Writing | 1439 | — |
| EQ-Bench Creative Writing | 1601 | — |
| LMArena Multi-Turn | 1456 | — |
Frequently asked questions
Is GLM-5 better than Qwen2.5 32B Instruct?
GLM-5 is the stronger model overall, scoring 46.1 to 30.1 on the Noometry Index.
Which is cheaper, GLM-5 or Qwen2.5 32B Instruct?
Qwen2.5 32B Instruct is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; GLM-5 lists at $1 and $3.20.
Is GLM-5 or Qwen2.5 32B Instruct better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 38.7 in the Noometry coding category.
Which has the bigger context window?
GLM-5 does, with 205K tokens against 131K.
How many benchmarks do GLM-5 and Qwen2.5 32B Instruct share?
4 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Qwen2.5 32B Instruct has 7.