Model comparison
GLM-5.1 vs gpt-oss-120b
GLM-5.1 is the stronger model overall, scoring 47.8 to 36.3 on the Noometry Index. gpt-oss-120b costs 31× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and gpt-oss-120b in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5.1 leads 66.9 to 46.5.
- The biggest single-benchmark swing is APEX-Agents: 40.9% for GLM-5.1 and 4.4% for gpt-oss-120b.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- GLM-5.1 accepts more context: 200K tokens versus 131K.
Side by side
| GLM-5.1 | gpt-oss-120b | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 47.8 | 36.3 |
| Released | 2026-04-07 | 2025-08-05 |
| Weights | Open | Open |
| Context window | 200K | 131K |
| Max output | 131K | 41K |
| Input $ / M tokens | $1.40 | $0.037 |
| Output $ / M tokens | $4.40 | $0.17 |
| Results tracked | 41 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
GLM-5.1: 48.7 (#55), gpt-oss-120b: 33.5 (#256)
| Benchmark | GLM-5.1 | gpt-oss-120b |
|---|---|---|
| SciCode | 43.8% | 36% |
| WeirdML | 57.1% | 48.2% |
| LMArena Coding | 1485 | 1380 |
| ALE-Bench | 887.1 | 575.62 |
| SWE-bench Verified | 74.2% | — |
| SWE-bench Verified (bash only) | — | 26% |
| Aider Polyglot | — | 41.8% |
| LMArena WebDev | 1508 | — |
| AlgoTune | — | 1.41 |
Agentic & Tool Use GLM-5.1 leads
GLM-5.1: 24.9 (#113), gpt-oss-120b: 12.2 (#153)
| Benchmark | GLM-5.1 | gpt-oss-120b |
|---|---|---|
| APEX-Agents | 40.9% | 4.4% |
| Vending-Bench 2 | 5,634 | -21.53 |
| Terminal-Bench | — | 18.7% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| METR Time Horizons | — | 56.6% |
Reasoning GLM-5.1 leads
GLM-5.1: 39.1 (#60), gpt-oss-120b: 20.0 (#245)
| Benchmark | GLM-5.1 | gpt-oss-120b |
|---|---|---|
| SimpleBench | 55.1% | 22.1% |
| CritPt | 4.6% | 1.1% |
| Chess Puzzles | 19% | 20% |
| LMArena Hard Prompts | 1472 | 1364 |
| Epoch Capabilities Index | 149.84 | 139.93 |
| Kagi LLM Benchmark | — | 58.6% |
| NYT Connections (extended) | 77.7% | — |
| Thematic Generalization | 69.8% | — |
| Mystery Game Puzzles | — | 2% |
| DTBench | — | 76.3% |
| LMCA | — | 22.1% |
| Surface Evolver Bench | — | 25% |
Math gpt-oss-120b leads
GLM-5.1: 49.7 (#60), gpt-oss-120b: 52.5 (#50)
| Benchmark | GLM-5.1 | gpt-oss-120b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 88.9% |
| LMArena Math | 1473 | 1389 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| Omni-MATH | — | 68.8% |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GLM-5.1 leads
GLM-5.1: 54.9 (#50), gpt-oss-120b: 42.4 (#96)
| Benchmark | GLM-5.1 | gpt-oss-120b |
|---|---|---|
| GPQA Diamond | 89.9% | 75.8% |
| LMArena Expert | 1476 | 1356 |
| SimpleQA Verified | 34% | — |
| MMLU-Pro | — | 79.5% |
| Confabulations | — | 15.7% |
| Vectara Hallucination Rate | — | 14.2% |
| GPQA (HELM) | — | 68.4% |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), gpt-oss-120b: 48.0 (#147)
| Benchmark | GLM-5.1 | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1447 | 1351 |
| LMArena Chinese | 1515 | 1385 |
| LMArena French | 1474 | 1369 |
| LMArena German | 1465 | 1353 |
| LMArena Japanese | 1434 | 1331 |
| LMArena Korean | 1418 | 1282 |
| LMArena Russian | 1454 | 1343 |
| LMArena Spanish | 1469 | 1389 |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.3 (#42), gpt-oss-120b: 69.3 (#173)
| Benchmark | GLM-5.1 | gpt-oss-120b |
|---|---|---|
| LMArena Instruction Following | 1451 | 1318 |
| IFEval | — | 83.6% |
Long Context GLM-5.1 leads
GLM-5.1: 44.9 (#53), gpt-oss-120b: 31.4 (#278)
| Benchmark | GLM-5.1 | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1466 | 1319 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference GLM-5.1 leads
GLM-5.1: 66.9 (#31), gpt-oss-120b: 46.5 (#217)
| Benchmark | GLM-5.1 | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1461 | 1365 |
| LMArena Creative Writing | 1453 | 1275 |
| EQ-Bench Creative Writing | 1592 | 961 |
| LMArena Multi-Turn | 1472 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| WildBench | — | 84.5% |
Frequently asked questions
Is GLM-5.1 better than gpt-oss-120b?
GLM-5.1 is the stronger model overall, scoring 47.8 to 36.3 on the Noometry Index. gpt-oss-120b costs 31× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Which is cheaper, GLM-5.1 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-5.1 lists at $1.40 and $4.40.
Is GLM-5.1 or gpt-oss-120b better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
GLM-5.1 does, with 200K tokens against 131K.
How many benchmarks do GLM-5.1 and gpt-oss-120b share?
29 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and gpt-oss-120b has 48.