Model comparison
GLM-4.5 vs Qwen3-Next 80B-A3B Instruct
Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 42.5 to 41.4 on the Noometry Index.
Last verified . 19 shared benchmarks.
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. GLM-4.5 scores higher in 3 categories and Qwen3-Next 80B-A3B Instruct in 5 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-Next 80B-A3B Instruct leads 41.3 to 35.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 57.9% for GLM-4.5 and 66.7% for Qwen3-Next 80B-A3B Instruct.
- Qwen3-Next 80B-A3B Instruct is cheaper at $0.50 / $2 per million input/output tokens, against $0.60 / $2.20 for GLM-4.5.
Side by side
| GLM-4.5 | Qwen3-Next 80B-A3B Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 41.4 | 42.5 |
| Released | 2025-07-27 | 2025-09 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 98K | 33K |
| Input $ / M tokens | $0.60 | $0.50 |
| Output $ / M tokens | $2.20 | $2 |
| Results tracked | 27 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-4.5: 41.1 (#121), Qwen3-Next 80B-A3B Instruct: 41.9 (#101)
| Benchmark | GLM-4.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Coding | 1434 | 1441 |
| SWE-bench Verified (bash only) | 54.2% | — |
| WeirdML | 40.6% | — |
| ALE-Bench | 344.82 | — |
| AlgoTune | 1.52 | — |
Reasoning Qwen3-Next 80B-A3B Instruct leads
GLM-4.5: 27.7 (#99), Qwen3-Next 80B-A3B Instruct: 30.1 (#79)
| Benchmark | GLM-4.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 57.9% | 66.7% |
| LMArena Hard Prompts | 1430 | 1428 |
Math Too close to call
GLM-4.5: 36.3 (#119), Qwen3-Next 80B-A3B Instruct: 36.3 (#118)
| Benchmark | GLM-4.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Math | 1427 | 1440 |
| Omni-MATH | — | 46.7% |
Knowledge Qwen3-Next 80B-A3B Instruct leads
GLM-4.5: 35.5 (#172), Qwen3-Next 80B-A3B Instruct: 41.3 (#102)
| Benchmark | GLM-4.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Expert | 1433 | 1416 |
| Humanity's Last Exam | 8.3% | — |
| MMLU-Pro | — | 78.6% |
| Confabulations | 11.3% | — |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 63% |
Multilingual Too close to call
GLM-4.5: 53.0 (#74), Qwen3-Next 80B-A3B Instruct: 52.3 (#88)
| Benchmark | GLM-4.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Non-English | 1417 | 1407 |
| LMArena Chinese | 1465 | 1461 |
| LMArena French | 1423 | 1415 |
| LMArena German | 1406 | 1416 |
| LMArena Japanese | 1416 | 1398 |
| LMArena Korean | 1382 | 1366 |
| LMArena Russian | 1414 | 1403 |
| LMArena Spanish | 1454 | 1436 |
Instruction Following GLM-4.5 leads
GLM-4.5: 74.3 (#100), Qwen3-Next 80B-A3B Instruct: 71.0 (#154)
| Benchmark | GLM-4.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Instruction Following | 1405 | 1388 |
| IFEval | — | 81% |
Long Context GLM-4.5 leads
GLM-4.5: 38.2 (#196), Qwen3-Next 80B-A3B Instruct: 37.0 (#218)
| Benchmark | GLM-4.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Fiction.LiveBench | 58.3% | 55.6% |
| LMArena Longer Query | 1413 | 1403 |
Writing & Preference Too close to call
GLM-4.5: 57.7 (#121), Qwen3-Next 80B-A3B Instruct: 58.2 (#116)
| Benchmark | GLM-4.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Text | 1430 | 1417 |
| LMArena Creative Writing | 1395 | 1333 |
| LMArena Multi-Turn | 1415 | 1415 |
| Short-Story Creative Writing | 73.4% | — |
| EQ-Bench Creative Writing | 1343 | — |
| WildBench | — | 80.7% |
Frequently asked questions
Is GLM-4.5 better than Qwen3-Next 80B-A3B Instruct?
Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 42.5 to 41.4 on the Noometry Index.
Which is cheaper, GLM-4.5 or Qwen3-Next 80B-A3B Instruct?
Qwen3-Next 80B-A3B Instruct is cheaper. It lists at $0.50 per million input tokens and $2 per million output tokens; GLM-4.5 lists at $0.60 and $2.20.
Is GLM-4.5 or Qwen3-Next 80B-A3B Instruct better for coding?
They score almost the same on coding (41.1 vs 41.9); test both on your own repository before choosing.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do GLM-4.5 and Qwen3-Next 80B-A3B Instruct share?
19 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Qwen3-Next 80B-A3B Instruct has 25.