GLM 4.6 vs gpt-oss-120b
Updated October 21, 2026. 58 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick GLM 4.6 for coding: it scores 52.2 on the Vibe Coding Index against 34.5 for gpt-oss-120b.
Pick gpt-oss-120b when output tokens cost 3.7x less, or when what matters is LiveCodeBench (Vals AI) or LiveCodeBench (Artificial Analysis run), where it leads.
- Shared results
- 58
- GLM 4.6 only
- 8
- gpt-oss-120b only
- 20
- Like-for-like categories
- 8 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, four public coding benchmarks
GLM 4.6
GLM 4.6 scores 52.2 against 34.5.
2 benchmarks behind each score
Intelligence
AA Intelligence Index
GLM 4.6
GLM 4.6 leads, 18.5 against 11.6.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only gpt-oss-120b has a AA Agentic Index result, 3.7.
Directional only
Reasoning
GPQA Diamond
gpt-oss-120b
gpt-oss-120b leads, 78.5% against 74.5%.
Same board, both measured
Math
AIME
GLM 4.6
GLM 4.6 leads, 92.7% against 92.6%.
Same board, both measured
Knowledge
MMLU Pro
GLM 4.6
GLM 4.6 leads, 82.2% against 79.2%.
Same board, both measured
Web design
Design Arena: websites
GLM 4.6
GLM 4.6 leads, 1174 against 968.
Same board, both measured
Long documents
Listed context window
GLM 4.6
GLM 4.6 takes 205K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
gpt-oss-120b
GLM 4.6 $0.0016, gpt-oss-120b $0.0004 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only gpt-oss-120b has the number, $0.51.
Directional only
At a glance
- Coding index
- GLM 4.6 52.2 from 2 benchmarks, gpt-oss-120b 34.5 from 2 benchmarks.
- Widest category
- Web design, 24.8 points apart on average over 6 shared benchmarks.
- Widest single gap
- SWE-bench Verified: GLM 4.6 68.2% against gpt-oss-120b 26.0%, 42.2 points apart on a 0 to 100 scale.
- Output price
- GLM 4.6 $2.20 against gpt-oss-120b $0.60 per million output tokens, 3.7x apart.
- Context window
- GLM 4.6 takes 205K tokens, gpt-oss-120b 131K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | GLM 4.6 | Bars | gpt-oss-120b | Ties |
|---|---|---|---|---|
| Coding | 6 | 3 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 3 | 3 | ||
| Math | 3 | 3 | ||
| Knowledge | 8 | 2 | ||
| Web design | 6 | 0 | ||
| General | 18 | 1 | ||
| All shared boards | 46 | 12 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index63
| Benchmark | GLM 4.6 | gpt-oss-120b | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 41.8% | Only gpt-oss-120b measured |
| SWE-bench Verified | 68.2% | 26.0% | GLM 4.6 |
| LMArena WebDev | 1341 | Not measured | Only GLM 4.6 measured |
| AA Coding Index | 45.8 | 30.4 | GLM 4.6 |
| LiveCodeBench (Vals AI) | 81.0% | 83.2% | gpt-oss-120b |
| SWE-bench Verified (Vals AI) | Not measured | 33.6% | Only gpt-oss-120b measured |
| Vibe Code Bench (Vals AI) | 3.1% | Not measured | Only GLM 4.6 measured |
| LiveCodeBench (Artificial Analysis run) | 69.5% | 87.8% | gpt-oss-120b |
| SciCode | Not measured | 34.0% | Only gpt-oss-120b measured |
| Terminal-Bench Hard (Artificial Analysis run) | 28.8% | 23.5% | GLM 4.6 |
| Terminal-Bench | 24.5% | 18.7% | GLM 4.6 |
| WeirdML | Not measured | 48.2% | Only gpt-oss-120b measured |
| ALE-Bench | 340.8 | 575.6 | gpt-oss-120b |
| LMArena Text: coding | 1449 | 1379 | GLM 4.6 |
| LMArena Text: software and IT | 1455 | 1387 | GLM 4.6 |
| LMArena WebDev: HTML | 1350 | Not measured | Only GLM 4.6 measured |
| Neither model has a result on the other 22 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GLM 4.6 | gpt-oss-120b | Leader |
|---|---|---|---|
| AA Intelligence Index | 18.5 | 11.6 | GLM 4.6 |
| Epoch Capabilities Index | Not measured | 139.8 | Only gpt-oss-120b measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GLM 4.6 | gpt-oss-120b | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 3.7 | Only gpt-oss-120b measured |
| Design Arena: agents building full-stack apps | 1029 | Not measured | Only GLM 4.6 measured |
| Design Arena: agents building mobile apps | 1096 | Not measured | Only GLM 4.6 measured |
| Design Arena: agents building Android apps | 1090 | Not measured | Only GLM 4.6 measured |
| Design Arena: agents building Godot games | 1180 | Not measured | Only GLM 4.6 measured |
| τ²-Bench Telecom | 76.9% | 65.8% | GLM 4.6 |
| APEX-Agents | Not measured | 4.4% | Only gpt-oss-120b measured |
| METR time horizons | Not measured | 56.6% | Only gpt-oss-120b measured |
| Vending-Bench 2 | Not measured | -$22 | Only gpt-oss-120b measured |
| Neither model has a result on the other 30 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index33
| Benchmark | GLM 4.6 | gpt-oss-120b | Leader |
|---|---|---|---|
| GPQA Diamond | 74.5% | 78.5% | gpt-oss-120b |
| GPQA Diamond (Artificial Analysis run) | 78.0% | 78.2% | gpt-oss-120b |
| Humanity's Last Exam (Artificial Analysis run) | 14.5% | 19.6% | gpt-oss-120b |
| GPQA Diamond (Epoch AI run) | Not measured | 75.8% | Only gpt-oss-120b measured |
| SimpleBench | Not measured | 22.1% | Only gpt-oss-120b measured |
| Mystery game puzzles | Not measured | 2.0% | Only gpt-oss-120b measured |
| LMArena Text: hard prompts | 1440 | 1364 | GLM 4.6 |
| LMArena Text: expert | 1432 | 1356 | GLM 4.6 |
| LMArena Text: hard prompts in English | 1445 | 1368 | GLM 4.6 |
| Neither model has a result on the other 12 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index33
| Benchmark | GLM 4.6 | gpt-oss-120b | Leader |
|---|---|---|---|
| AIME | 92.7% | 92.6% | GLM 4.6 |
| MATH 500 (Vals AI) | Not measured | 94.8% | Only gpt-oss-120b measured |
| MGSM (Vals AI) | 89.8% | 92.0% | gpt-oss-120b |
| AA Math Index | 86.0 | 93.4 | gpt-oss-120b |
| AIME 2025 (Artificial Analysis run) | 86.0% | 93.4% | gpt-oss-120b |
| OTIS Mock AIME | Not measured | 88.9% | Only gpt-oss-120b measured |
| LMArena Text: math | 1432 | 1389 | GLM 4.6 |
| LMArena Text: mathematical work | 1447 | 1386 | GLM 4.6 |
| Neither model has a result on the other 5 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index82
| Benchmark | GLM 4.6 | gpt-oss-120b | Leader |
|---|---|---|---|
| MMLU Pro | 82.2% | 79.2% | GLM 4.6 |
| LegalBench (Vals AI) | 79.6% | 75.9% | GLM 4.6 |
| CaseLaw (Vals AI) | Not measured | 48.8% | Only gpt-oss-120b measured |
| CorpFin (Vals AI) | 56.8% | 58.2% | gpt-oss-120b |
| TaxEval (Vals AI) | 66.2% | 71.6% | gpt-oss-120b |
| MedQA (Vals AI) | 92.2% | 91.4% | GLM 4.6 |
| MMLU Pro (Artificial Analysis run) | 82.9% | 80.8% | GLM 4.6 |
| LMArena Text: science | 1456 | 1382 | GLM 4.6 |
| LMArena Text: medicine and healthcare | 1455 | 1388 | GLM 4.6 |
| LMArena Text: legal and government | 1448 | 1355 | GLM 4.6 |
| LMArena Text: business and finance | 1416 | 1359 | GLM 4.6 |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | GLM 4.6 | gpt-oss-120b | Leader |
|---|---|---|---|
| Design Arena: websites | 1174 | 968 | GLM 4.6 |
| Design Arena: UI components | 1147 | 927 | GLM 4.6 |
| Design Arena: game dev | 1151 | 992 | GLM 4.6 |
| Design Arena: data viz | 1161 | 987 | GLM 4.6 |
| Design Arena: 3D | 1129 | 901 | GLM 4.6 |
| Design Arena: all code categories | 1166 | 963 | GLM 4.6 |
| Design Arena: SVG | 1108 | Not measured | Only GLM 4.6 measured |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index181
| Benchmark | GLM 4.6 | gpt-oss-120b | Leader |
|---|---|---|---|
| IFBench | 43.4% | 69.0% | gpt-oss-120b |
| Long context reasoning (AA-LCR) | 54.0% | 52.0% | GLM 4.6 |
| DTBench | Not measured | 76.3% | Only gpt-oss-120b measured |
| LMCA | Not measured | 22.1% | Only gpt-oss-120b measured |
| Fiction.LiveBench | Not measured | 44.4% | Only gpt-oss-120b measured |
| Creative writing (Lech Mazur) | Not measured | 77.1% | Only gpt-oss-120b measured |
| Surface Evolver Bench | Not measured | 25.0% | Only gpt-oss-120b measured |
| LMArena Text | 1440 | 1366 | GLM 4.6 |
| LMArena Text: instruction following | 1410 | 1318 | GLM 4.6 |
| LMArena Text: creative writing | 1412 | 1274 | GLM 4.6 |
| LMArena Text: English | 1449 | 1375 | GLM 4.6 |
| LMArena Text: non-English | 1426 | 1351 | GLM 4.6 |
| LMArena Text: Chinese | 1499 | 1385 | GLM 4.6 |
| LMArena Text: German | 1447 | 1353 | GLM 4.6 |
| LMArena Text: Japanese | 1393 | 1331 | GLM 4.6 |
| LMArena Text: Korean | 1400 | 1282 | GLM 4.6 |
| LMArena Text: French | 1459 | 1370 | GLM 4.6 |
| LMArena Text: Spanish | 1436 | 1389 | GLM 4.6 |
| LMArena Text: Russian | 1418 | 1343 | GLM 4.6 |
| LMArena Text: Polish | 1447 | 1353 | GLM 4.6 |
| LMArena Text: multi-turn | 1427 | 1340 | GLM 4.6 |
| LMArena Text: longer queries | 1422 | 1319 | GLM 4.6 |
| LMArena Text: writing and language | 1415 | 1306 | GLM 4.6 |
| LMArena Text: entertainment and media | 1409 | 1292 | GLM 4.6 |
| Neither model has a result on the other 22 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GLM 4.6 | gpt-oss-120b | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
gpt-oss-120b costs less
Repository review
50K input + 3K output tokens
gpt-oss-120b costs less
Agent loop
200K input + 10K output tokens
gpt-oss-120b costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Z.ai GLM 4.6 | OpenAI gpt-oss-120b |
|---|---|---|
| Maker | Z.ai | OpenAI |
| Weights | Open weights | Open weights |
| Released | September 30, 2025 | August 5, 2025 |
| Context window | 205K | 131K |
| Input $/Mtok | $0.55 | $0.15 |
| Output $/Mtok | $2.20 | $0.60 |
| Coding index | 52.2 | 34.5 |
| Independent measurements behind it | 2 | 2 |
| Cost per solved task | Not computable | $0.51 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GLM 4.6 better than gpt-oss-120b for coding?
Pick GLM 4.6 for coding: it scores 52.2 on the Vibe Coding Index against 34.5 for gpt-oss-120b. Pick gpt-oss-120b when output tokens cost 3.7x less, or when what matters is LiveCodeBench (Vals AI) or LiveCodeBench (Artificial Analysis run), where it leads.
Which is cheaper, GLM 4.6 or gpt-oss-120b?
GLM 4.6 costs $0.55 per million input tokens and $2.20 per million output tokens; gpt-oss-120b costs $0.15 and $0.60. Cost per solved task is known for gpt-oss-120b only.
Which has the bigger context window, GLM 4.6 or gpt-oss-120b?
GLM 4.6, with 205K tokens against 131K.
How many benchmarks is the GLM 4.6 vs gpt-oss-120b comparison based on?
58 benchmarks have a result for both models as of October 21, 2026. GLM 4.6's coding index rests on 2 independent benchmarks and gpt-oss-120b's on 2. Where only one model has a result, the page says so instead of naming a winner.