Model comparison
GLM-4.6 vs gpt-oss-120b
GLM-4.6 is the stronger model overall, scoring 41.4 to 36.3 on the Noometry Index. gpt-oss-120b costs 14× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. GLM-4.6 scores higher in 7 categories and gpt-oss-120b in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GLM-4.6 leads 32.3 to 12.2.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 55.4% for GLM-4.6 and 26% for gpt-oss-120b.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- GLM-4.6 accepts more context: 205K tokens versus 131K.
Side by side
| GLM-4.6 | gpt-oss-120b | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 41.4 | 36.3 |
| Released | 2025-09-30 | 2025-08-05 |
| Weights | Open | Open |
| Context window | 205K | 131K |
| Max output | 131K | 41K |
| Input $ / M tokens | $0.60 | $0.037 |
| Output $ / M tokens | $2.20 | $0.17 |
| Results tracked | 29 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
GLM-4.6: 40.1 (#148), gpt-oss-120b: 33.5 (#256)
| Benchmark | GLM-4.6 | gpt-oss-120b |
|---|---|---|
| SWE-bench Verified (bash only) | 55.4% | 26% |
| SciCode | 38.4% | 36% |
| LMArena Coding | 1449 | 1380 |
| ALE-Bench | 340.82 | 575.62 |
| Aider Polyglot | — | 41.8% |
| LMArena WebDev | 1340 | — |
| WeirdML | — | 48.2% |
| AlgoTune | — | 1.41 |
Agentic & Tool Use GLM-4.6 leads
GLM-4.6: 32.3 (#66), gpt-oss-120b: 12.2 (#153)
| Benchmark | GLM-4.6 | gpt-oss-120b |
|---|---|---|
| Terminal-Bench | 24.5% | 18.7% |
| APEX-Agents | — | 4.4% |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| METR Time Horizons | — | 56.6% |
| Vending-Bench 2 | — | -21.53 |
Reasoning GLM-4.6 leads
GLM-4.6: 23.7 (#172), gpt-oss-120b: 20.0 (#245)
| Benchmark | GLM-4.6 | gpt-oss-120b |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | 58.6% |
| CritPt | 1.1% | 1.1% |
| LMArena Hard Prompts | 1440 | 1364 |
| SimpleBench | — | 22.1% |
| Chess Puzzles | — | 20% |
| Mystery Game Puzzles | — | 2% |
| DTBench | — | 76.3% |
| LMCA | — | 22.1% |
| Surface Evolver Bench | — | 25% |
| Epoch Capabilities Index | — | 139.93 |
Math gpt-oss-120b leads
GLM-4.6: 39.1 (#111), gpt-oss-120b: 52.5 (#50)
| Benchmark | GLM-4.6 | gpt-oss-120b |
|---|---|---|
| LMArena Math | 1432 | 1389 |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| Omni-MATH | — | 68.8% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge gpt-oss-120b leads
GLM-4.6: 40.2 (#124), gpt-oss-120b: 42.4 (#96)
| Benchmark | GLM-4.6 | gpt-oss-120b |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 14.2% |
| LMArena Expert | 1431 | 1356 |
| GPQA Diamond | — | 75.8% |
| MMLU-Pro | — | 79.5% |
| Confabulations | — | 15.7% |
| GPQA (HELM) | — | 68.4% |
Multilingual GLM-4.6 leads
GLM-4.6: 53.5 (#66), gpt-oss-120b: 48.0 (#147)
| Benchmark | GLM-4.6 | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1426 | 1351 |
| LMArena Chinese | 1499 | 1385 |
| LMArena French | 1459 | 1369 |
| LMArena German | 1447 | 1353 |
| LMArena Japanese | 1393 | 1331 |
| LMArena Korean | 1400 | 1282 |
| LMArena Russian | 1419 | 1343 |
| LMArena Spanish | 1436 | 1389 |
Instruction Following GLM-4.6 leads
GLM-4.6: 74.3 (#98), gpt-oss-120b: 69.3 (#173)
| Benchmark | GLM-4.6 | gpt-oss-120b |
|---|---|---|
| LMArena Instruction Following | 1410 | 1318 |
| IFEval | — | 83.6% |
Long Context GLM-4.6 leads
GLM-4.6: 43.4 (#94), gpt-oss-120b: 31.4 (#278)
| Benchmark | GLM-4.6 | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1422 | 1319 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference GLM-4.6 leads
GLM-4.6: 61.1 (#90), gpt-oss-120b: 46.5 (#217)
| Benchmark | GLM-4.6 | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1440 | 1365 |
| LMArena Creative Writing | 1411 | 1275 |
| EQ-Bench Creative Writing | 1411 | 961 |
| LMArena Multi-Turn | 1427 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| WildBench | — | 84.5% |
Frequently asked questions
Is GLM-4.6 better than gpt-oss-120b?
GLM-4.6 is the stronger model overall, scoring 41.4 to 36.3 on the Noometry Index. gpt-oss-120b costs 14× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.
Which is cheaper, GLM-4.6 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-4.6 lists at $0.60 and $2.20.
Is GLM-4.6 or gpt-oss-120b better for coding?
GLM-4.6 scores higher on coding benchmarks: 40.1 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
GLM-4.6 does, with 205K tokens against 131K.
How many benchmarks do GLM-4.6 and gpt-oss-120b share?
25 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and gpt-oss-120b has 48.