Model comparison
GLM-5.3-Flash vs gpt-oss-120b
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 36.3 on the Noometry Index. gpt-oss-120b costs 3.4× less per token, which makes it the better buy when GLM-5.3-Flash's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. GLM-5.3-Flash scores higher in 9 categories and gpt-oss-120b in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.3-Flash leads 48.0 to 20.0.
- The biggest single-benchmark swing is APEX-Agents: 52.8% for GLM-5.3-Flash and 4.4% for gpt-oss-120b.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.15 / $0.50 for GLM-5.3-Flash.
- GLM-5.3-Flash accepts more context: 1M tokens versus 131K.
Side by side
| GLM-5.3-Flash | gpt-oss-120b | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 51.8 | 36.3 |
| Released | 2026-08-20 | 2025-08-05 |
| Weights | Open | Open |
| Context window | 1M | 131K |
| Max output | 131K | 41K |
| Input $ / M tokens | $0.15 | $0.037 |
| Output $ / M tokens | $0.50 | $0.17 |
| Results tracked | 40 | 48 |
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: 53.1 (#31), gpt-oss-120b: 33.5 (#256)
| Benchmark | GLM-5.3-Flash | gpt-oss-120b |
|---|---|---|
| SciCode | 51.6% | 36% |
| LMArena Coding | 1508 | 1380 |
| ALE-Bench | 303.55 | 575.62 |
| DeepSWE | 63.4% | — |
| FrontierCode | 31.8% | — |
| SWE-bench Verified (bash only) | — | 26% |
| Aider Polyglot | — | 41.8% |
| CursorBench | 36.8% | — |
| LMArena WebDev | 1609 | — |
| FrontierSWE | 18.1% | — |
| WeirdML | — | 48.2% |
| AlgoTune | — | 1.41 |
Agentic & Tool Use GLM-5.3-Flash leads
GLM-5.3-Flash: 34.2 (#47), gpt-oss-120b: 12.2 (#153)
| Benchmark | GLM-5.3-Flash | gpt-oss-120b |
|---|---|---|
| APEX-Agents | 52.8% | 4.4% |
| Terminal-Bench | — | 18.7% |
| GDP.pdf | 14% | — |
| METR Time Horizons | — | 56.6% |
| Vending-Bench 2 | — | -21.53 |
Reasoning GLM-5.3-Flash leads
GLM-5.3-Flash: 48.0 (#42), gpt-oss-120b: 20.0 (#245)
| Benchmark | GLM-5.3-Flash | gpt-oss-120b |
|---|---|---|
| CritPt | 15.4% | 1.1% |
| Chess Puzzles | 14% | 20% |
| LMArena Hard Prompts | 1491 | 1364 |
| Mystery Game Puzzles | 8% | 2% |
| Surface Evolver Bench | 52.5% | 25% |
| Epoch Capabilities Index | 151.88 | 139.93 |
| ARC-AGI-2 | 65.8% | — |
| SimpleBench | — | 22.1% |
| Kagi LLM Benchmark | — | 58.6% |
| ARC-AGI-1 | 91% | — |
| DTBench | — | 76.3% |
| LMCA | — | 22.1% |
| Bench to the Future 3 | 0.15 | — |
Math Too close to call
GLM-5.3-Flash: 53.3 (#47), gpt-oss-120b: 52.5 (#50)
| Benchmark | GLM-5.3-Flash | gpt-oss-120b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.9% | 88.9% |
| LMArena Math | 1500 | 1389 |
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 21% | — |
| Omni-MATH | — | 68.8% |
Knowledge GLM-5.3-Flash leads
GLM-5.3-Flash: 58.4 (#36), gpt-oss-120b: 42.4 (#96)
| Benchmark | GLM-5.3-Flash | gpt-oss-120b |
|---|---|---|
| GPQA Diamond | 90.2% | 75.8% |
| LMArena Expert | 1513 | 1356 |
| MMLU-Pro | — | 79.5% |
| Confabulations | — | 15.7% |
| Vectara Hallucination Rate | — | 14.2% |
| GPQA (HELM) | — | 68.4% |
Multimodal Not comparable
GLM-5.3-Flash: 42.8 (#27), gpt-oss-120b: —
| Benchmark | GLM-5.3-Flash | gpt-oss-120b |
|---|---|---|
| LMArena Vision | 1296 | — |
Multilingual GLM-5.3-Flash leads
GLM-5.3-Flash: 56.0 (#25), gpt-oss-120b: 48.0 (#147)
| Benchmark | GLM-5.3-Flash | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1462 | 1351 |
| LMArena Chinese | 1527 | 1385 |
| LMArena French | 1496 | 1369 |
| LMArena German | 1470 | 1353 |
| LMArena Japanese | 1429 | 1331 |
| LMArena Korean | 1446 | 1282 |
| LMArena Russian | 1469 | 1343 |
| LMArena Spanish | 1471 | 1389 |
Instruction Following GLM-5.3-Flash leads
GLM-5.3-Flash: 77.5 (#20), gpt-oss-120b: 69.3 (#173)
| Benchmark | GLM-5.3-Flash | gpt-oss-120b |
|---|---|---|
| LMArena Instruction Following | 1478 | 1318 |
| IFEval | — | 83.6% |
Long Context GLM-5.3-Flash leads
GLM-5.3-Flash: 45.4 (#39), gpt-oss-120b: 31.4 (#278)
| Benchmark | GLM-5.3-Flash | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1482 | 1319 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference GLM-5.3-Flash leads
GLM-5.3-Flash: 65.3 (#50), gpt-oss-120b: 46.5 (#217)
| Benchmark | GLM-5.3-Flash | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1471 | 1365 |
| LMArena Creative Writing | 1442 | 1275 |
| LMArena Multi-Turn | 1467 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| EQ-Bench Creative Writing | — | 961 |
| WildBench | — | 84.5% |
Frequently asked questions
Is GLM-5.3-Flash better than gpt-oss-120b?
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 36.3 on the Noometry Index. gpt-oss-120b costs 3.4× less per token, which makes it the better buy when GLM-5.3-Flash's lead doesn't matter for your workload.
Which is cheaper, GLM-5.3-Flash or gpt-oss-120b?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; GLM-5.3-Flash lists at $0.15 and $0.50.
Is GLM-5.3-Flash or gpt-oss-120b better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.1 versus 33.5 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 gpt-oss-120b share?
27 benchmarks have published results for both models. GLM-5.3-Flash has 40 scored results on Noometry and gpt-oss-120b has 48.