Model comparison
GLM-5.3-Flash vs Qwen3-Next 80B-A3B Instruct
GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 42.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. GLM-5.3-Flash scores higher in 8 categories and Qwen3-Next 80B-A3B Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.3-Flash leads 58.4 to 41.3.
- GLM-5.3-Flash is cheaper at $0.15 / $0.50 per million input/output tokens, against $0.50 / $2 for Qwen3-Next 80B-A3B Instruct.
- GLM-5.3-Flash accepts more context: 1M tokens versus 131K.
Side by side
| GLM-5.3-Flash | Qwen3-Next 80B-A3B Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 49.6 | 42.5 |
| Released | 2026-08-20 | 2025-09 |
| Weights | Open | Open |
| Context window | 1M | 131K |
| Max output | 131K | 33K |
| Input $ / M tokens | $0.15 | $0.50 |
| Output $ / M tokens | $0.50 | $2 |
| Results tracked | 36 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3-Flash leads
GLM-5.3-Flash: 53.7 (#26), Qwen3-Next 80B-A3B Instruct: 41.9 (#101)
| Benchmark | GLM-5.3-Flash | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Coding | 1506 | 1441 |
| DeepSWE | 63.4% | — |
| FrontierCode | 31.8% | — |
| LMArena WebDev | 1614 | — |
| SciCode | 51.6% | — |
| ALE-Bench | 303.55 | — |
Agentic & Tool Use Not comparable
GLM-5.3-Flash: 34.3 (#41), Qwen3-Next 80B-A3B Instruct: —
| Benchmark | GLM-5.3-Flash | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| APEX-Agents | 52.8% | — |
| GDP.pdf | 14% | — |
Reasoning GLM-5.3-Flash leads
GLM-5.3-Flash: 31.7 (#69), Qwen3-Next 80B-A3B Instruct: 30.1 (#79)
| Benchmark | GLM-5.3-Flash | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1490 | 1428 |
| Kagi LLM Benchmark | — | 66.7% |
| CritPt | 15.4% | — |
| Chess Puzzles | 14% | — |
| Mystery Game Puzzles | 8% | — |
| Surface Evolver Bench | 52.5% | — |
| Bench to the Future 3 | 0.15 | — |
| Epoch Capabilities Index | 151.9 | — |
Math GLM-5.3-Flash leads
GLM-5.3-Flash: 53.1 (#38), Qwen3-Next 80B-A3B Instruct: 36.3 (#118)
| Benchmark | GLM-5.3-Flash | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Math | 1499 | 1440 |
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 93.9% | — |
| ProofBench | 21% | — |
| Omni-MATH | — | 46.7% |
Knowledge GLM-5.3-Flash leads
GLM-5.3-Flash: 58.4 (#33), Qwen3-Next 80B-A3B Instruct: 41.3 (#102)
| Benchmark | GLM-5.3-Flash | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Expert | 1512 | 1416 |
| GPQA Diamond | 90.2% | — |
| MMLU-Pro | — | 78.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 63% |
Multimodal Not comparable
GLM-5.3-Flash: 42.6 (#25), Qwen3-Next 80B-A3B Instruct: —
| Benchmark | GLM-5.3-Flash | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Vision | 1304 | — |
Multilingual GLM-5.3-Flash leads
GLM-5.3-Flash: 56.2 (#24), Qwen3-Next 80B-A3B Instruct: 52.3 (#88)
| Benchmark | GLM-5.3-Flash | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Non-English | 1462 | 1407 |
| LMArena Chinese | 1529 | 1461 |
| LMArena French | 1495 | 1415 |
| LMArena German | 1457 | 1416 |
| LMArena Japanese | 1420 | 1398 |
| LMArena Korean | 1443 | 1366 |
| LMArena Russian | 1472 | 1403 |
| LMArena Spanish | 1471 | 1436 |
Instruction Following GLM-5.3-Flash leads
GLM-5.3-Flash: 77.8 (#17), Qwen3-Next 80B-A3B Instruct: 71.0 (#154)
| Benchmark | GLM-5.3-Flash | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Instruction Following | 1480 | 1388 |
| IFEval | — | 81% |
Long Context GLM-5.3-Flash leads
GLM-5.3-Flash: 45.3 (#41), Qwen3-Next 80B-A3B Instruct: 37.0 (#218)
| Benchmark | GLM-5.3-Flash | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Longer Query | 1479 | 1403 |
| Fiction.LiveBench | — | 55.6% |
Writing & Preference GLM-5.3-Flash leads
GLM-5.3-Flash: 65.4 (#49), Qwen3-Next 80B-A3B Instruct: 58.2 (#116)
| Benchmark | GLM-5.3-Flash | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Text | 1471 | 1417 |
| LMArena Creative Writing | 1440 | 1333 |
| LMArena Multi-Turn | 1471 | 1415 |
| WildBench | — | 80.7% |
Frequently asked questions
Is GLM-5.3-Flash better than Qwen3-Next 80B-A3B Instruct?
GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 42.5 on the Noometry Index.
Which is cheaper, GLM-5.3-Flash or Qwen3-Next 80B-A3B Instruct?
GLM-5.3-Flash is cheaper. It lists at $0.15 per million input tokens and $0.50 per million output tokens; Qwen3-Next 80B-A3B Instruct lists at $0.50 and $2.
Is GLM-5.3-Flash or Qwen3-Next 80B-A3B Instruct better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.7 versus 41.9 in the Noometry coding category.
Which has the bigger context window?
GLM-5.3-Flash does, with 1M tokens against 131K.
How many benchmarks do GLM-5.3-Flash and Qwen3-Next 80B-A3B Instruct share?
17 benchmarks have published results for both models. GLM-5.3-Flash has 36 scored results on Noometry and Qwen3-Next 80B-A3B Instruct has 25.