Model comparison
GLM-4.5 vs Qwen3 8B
GLM-4.5 is the stronger model overall, scoring 42.0 to 33.7 on the Noometry Index. Qwen3 8B costs 3.2× less per token, which makes it the better buy when GLM-4.5's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. GLM-4.5 scores higher in 4 categories and Qwen3 8B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-4.5 leads 28.6 to 16.6.
- Qwen3 8B is cheaper at $0.18 / $0.70 per million input/output tokens, against $0.60 / $2.20 for GLM-4.5.
Side by side
| GLM-4.5 | Qwen3 8B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 42.0 | 33.7 |
| Released | 2025-07-27 | 2025-04 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 98K | 8K |
| Input $ / M tokens | $0.60 | $0.18 |
| Output $ / M tokens | $2.20 | $0.70 |
| Results tracked | 27 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5 leads
GLM-4.5: 41.4 (#125), Qwen3 8B: 34.0 (#248)
| Benchmark | GLM-4.5 | Qwen3 8B |
|---|---|---|
| SWE-bench Verified (bash only) | 54.2% | — |
| SciCode | — | 22.6% |
| WeirdML | 40.6% | — |
| LMArena Coding | 1434 | — |
| ALE-Bench | 344.82 | — |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Not comparable
GLM-4.5: —, Qwen3 8B: 30.2 (#78)
| Benchmark | GLM-4.5 | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 42.6% |
Reasoning GLM-4.5 leads
GLM-4.5: 28.6 (#100), Qwen3 8B: 16.6 (#303)
| Benchmark | GLM-4.5 | Qwen3 8B |
|---|---|---|
| Kagi LLM Benchmark | 57.9% | — |
| CritPt | — | 0% |
| Chess Puzzles | — | 5% |
| LMArena Hard Prompts | 1429 | — |
| DTBench | — | 59.7% |
| LMCA | — | 8.8% |
| Epoch Capabilities Index | — | 136.17 |
Math GLM-4.5 leads
GLM-4.5: 39.0 (#116), Qwen3 8B: 34.9 (#191)
| Benchmark | GLM-4.5 | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 56.1% |
| LMArena Math | 1427 | — |
Knowledge Too close to call
GLM-4.5: 35.9 (#179), Qwen3 8B: 36.1 (#173)
| Benchmark | GLM-4.5 | Qwen3 8B |
|---|---|---|
| GPQA Diamond | — | 56.8% |
| Humanity's Last Exam | 8.3% | — |
| Confabulations | 11.3% | — |
| Vectara Hallucination Rate | — | 4.8% |
| LMArena Expert | 1433 | — |
Multilingual Not comparable
GLM-4.5: 52.8 (#77), Qwen3 8B: —
| Benchmark | GLM-4.5 | Qwen3 8B |
|---|---|---|
| LMArena Non-English | 1417 | — |
| LMArena Chinese | 1465 | — |
| LMArena French | 1418 | — |
| LMArena German | 1407 | — |
| LMArena Japanese | 1415 | — |
| LMArena Korean | 1380 | — |
| LMArena Russian | 1414 | — |
| LMArena Spanish | 1454 | — |
Instruction Following Not comparable
GLM-4.5: 74.1 (#104), Qwen3 8B: —
| Benchmark | GLM-4.5 | Qwen3 8B |
|---|---|---|
| LMArena Instruction Following | 1404 | — |
Long Context Too close to call
GLM-4.5: 38.2 (#201), Qwen3 8B: 37.9 (#210)
| Benchmark | GLM-4.5 | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | 58.3% | 62.1% |
| LMArena Longer Query | 1412 | — |
Writing & Preference Not comparable
GLM-4.5: 57.5 (#127), Qwen3 8B: —
| Benchmark | GLM-4.5 | Qwen3 8B |
|---|---|---|
| LMArena Text | 1430 | — |
| LMArena Creative Writing | 1395 | — |
| Short-Story Creative Writing | 73.4% | — |
| EQ-Bench Creative Writing | 1343 | — |
| LMArena Multi-Turn | 1415 | — |
Frequently asked questions
Is GLM-4.5 better than Qwen3 8B?
GLM-4.5 is the stronger model overall, scoring 42.0 to 33.7 on the Noometry Index. Qwen3 8B costs 3.2× less per token, which makes it the better buy when GLM-4.5's lead doesn't matter for your workload.
Which is cheaper, GLM-4.5 or Qwen3 8B?
Qwen3 8B is cheaper. It lists at $0.18 per million input tokens and $0.70 per million output tokens; GLM-4.5 lists at $0.60 and $2.20.
Is GLM-4.5 or Qwen3 8B better for coding?
GLM-4.5 scores higher on coding benchmarks: 41.4 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do GLM-4.5 and Qwen3 8B share?
1 benchmark has published results for both models. GLM-4.5 has 27 scored results on Noometry and Qwen3 8B has 11.