Model comparison
GLM-4.6V vs gpt-oss-20b
GLM-4.6V is the stronger model overall, scoring 41.3 to 32.5 on the Noometry Index. gpt-oss-20b costs 13× less per token, which makes it the better buy when GLM-4.6V's lead doesn't matter for your workload.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. GLM-4.6V scores higher in 7 categories and gpt-oss-20b in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.6V leads 56.6 to 35.5.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.30 / $0.90 for GLM-4.6V.
- gpt-oss-20b accepts more context: 131K tokens versus 128K.
Side by side
| GLM-4.6V | gpt-oss-20b | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 41.3 | 32.5 |
| Released | 2025-12-08 | 2025-08-05 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 33K | 16K |
| Input $ / M tokens | $0.30 | $0.018 |
| Output $ / M tokens | $0.90 | $0.09 |
| Results tracked | 12 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6V leads
GLM-4.6V: 40.9 (#128), gpt-oss-20b: 37.6 (#192)
| Benchmark | GLM-4.6V | gpt-oss-20b |
|---|---|---|
| LMArena Coding | 1390 | 1306 |
| SciCode | — | 34.4% |
| WeirdML | — | 40.9% |
| ALE-Bench | — | 566.05 |
Agentic & Tool Use Not comparable
GLM-4.6V: —, gpt-oss-20b: 9.3 (#154)
| Benchmark | GLM-4.6V | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |
Reasoning GLM-4.6V leads
GLM-4.6V: 27.6 (#115), gpt-oss-20b: 19.3 (#261)
| Benchmark | GLM-4.6V | gpt-oss-20b |
|---|---|---|
| LMArena Hard Prompts | 1368 | 1274 |
| Kagi LLM Benchmark | — | 53.2% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 4% |
| DTBench | — | 68% |
| LMCA | — | 14.5% |
| Epoch Capabilities Index | — | 137.82 |
Math Not comparable
GLM-4.6V: —, gpt-oss-20b: 39.4 (#103)
| Benchmark | GLM-4.6V | gpt-oss-20b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 65.3% |
| Omni-MATH | — | 56.5% |
| LMArena Math | — | 1317 |
Knowledge GLM-4.6V leads
GLM-4.6V: 38.0 (#149), gpt-oss-20b: 34.6 (#195)
| Benchmark | GLM-4.6V | gpt-oss-20b |
|---|---|---|
| LMArena Expert | 1371 | 1258 |
| GPQA Diamond | — | 60.8% |
| MMLU-Pro | — | 74% |
| GPQA (HELM) | — | 59.4% |
Multimodal Not comparable
GLM-4.6V: 34.8 (#90), gpt-oss-20b: —
| Benchmark | GLM-4.6V | gpt-oss-20b |
|---|---|---|
| LMArena Vision | 1164 | — |
Multilingual GLM-4.6V leads
GLM-4.6V: 48.6 (#141), gpt-oss-20b: 42.2 (#197)
| Benchmark | GLM-4.6V | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 1359 | 1268 |
| LMArena Chinese | 1425 | 1314 |
| LMArena Russian | 1340 | 1278 |
| LMArena German | — | 1255 |
| LMArena Japanese | — | 1244 |
| LMArena Korean | — | 1236 |
| LMArena Spanish | — | 1267 |
Instruction Following GLM-4.6V leads
GLM-4.6V: 71.4 (#151), gpt-oss-20b: 61.8 (#240)
| Benchmark | GLM-4.6V | gpt-oss-20b |
|---|---|---|
| LMArena Instruction Following | 1352 | 1236 |
| IFEval | — | 73.2% |
Long Context GLM-4.6V leads
GLM-4.6V: 41.3 (#143), gpt-oss-20b: 37.9 (#209)
| Benchmark | GLM-4.6V | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | 1358 | 1250 |
Writing & Preference GLM-4.6V leads
GLM-4.6V: 56.6 (#137), gpt-oss-20b: 35.5 (#265)
| Benchmark | GLM-4.6V | gpt-oss-20b |
|---|---|---|
| LMArena Text | 1377 | 1287 |
| LMArena Creative Writing | 1347 | 1201 |
| LMArena Multi-Turn | 1360 | 1268 |
| EQ-Bench Creative Writing | — | 666 |
| WildBench | — | 73.7% |
Frequently asked questions
Is GLM-4.6V better than gpt-oss-20b?
GLM-4.6V is the stronger model overall, scoring 41.3 to 32.5 on the Noometry Index. gpt-oss-20b costs 13× less per token, which makes it the better buy when GLM-4.6V's lead doesn't matter for your workload.
Which is cheaper, GLM-4.6V or gpt-oss-20b?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; GLM-4.6V lists at $0.30 and $0.90.
Is GLM-4.6V or gpt-oss-20b better for coding?
GLM-4.6V scores higher on coding benchmarks: 40.9 versus 37.6 in the Noometry coding category.
Which has the bigger context window?
gpt-oss-20b does, with 131K tokens against 128K.
How many benchmarks do GLM-4.6V and gpt-oss-20b share?
11 benchmarks have published results for both models. GLM-4.6V has 12 scored results on Noometry and gpt-oss-20b has 34.