GLM 4.6 vs GPT-5 Nano
Updated October 21, 2026. 54 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 34.8 for GPT-5 Nano.
Pick GPT-5 Nano when output tokens cost 5.5x less, or when the context window is larger, 400K against 205K tokens.
- Shared results
- 54
- GLM 4.6 only
- 12
- GPT-5 Nano only
- 31
- 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 34.8.
2 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
GLM 4.6
GLM 4.6 leads, 18.5 against 13.0.
Same board, both measured
Reasoning
GPQA Diamond
GLM 4.6
GLM 4.6 leads, 74.5% against 63.4%.
Same board, both measured
Math
AIME
GLM 4.6
GLM 4.6 leads, 92.7% against 81.2%.
Same board, both measured
Knowledge
MMLU Pro
GLM 4.6
GLM 4.6 leads, 82.2% against 76.1%.
Same board, both measured
Web design
Design Arena: websites
GLM 4.6
GLM 4.6 leads, 1174 against 1101.
Same board, both measured
Long documents
Listed context window
GPT-5 Nano
GPT-5 Nano takes 400K tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-5 Nano
GLM 4.6 $0.0016, GPT-5 Nano $0.0003 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5 Nano has the number, $0.109.
Directional only
At a glance
- Coding index
- GLM 4.6 52.2 from 2 benchmarks, GPT-5 Nano 34.8 from 1 benchmark.
- Widest category
- Agentic work, 40.4 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: GLM 4.6 76.9% against GPT-5 Nano 36.5%, 40.4 points apart on a 0 to 100 scale.
- Output price
- GLM 4.6 $2.20 against GPT-5 Nano $0.40 per million output tokens, 5.5x apart.
- Context window
- GLM 4.6 takes 205K tokens, GPT-5 Nano 400K.
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-5 Nano | Ties |
|---|---|---|---|---|
| Coding | 6 | 1 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 6 | 0 | ||
| Math | 6 | 0 | ||
| Knowledge | 7 | 2 | ||
| Web design | 6 | 0 | ||
| General | 17 | 1 | ||
| All shared boards | 50 | 4 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index61
| Benchmark | GLM 4.6 | GPT-5 Nano | Leader |
|---|---|---|---|
| SWE-bench Verified | 68.2% | 34.8% | GLM 4.6 |
| LMArena WebDev | 1341 | Not measured | Only GLM 4.6 measured |
| AA Coding Index | 45.8 | Not measured | Only GLM 4.6 measured |
| LiveCodeBench (Vals AI) | 81.0% | 70.2% | GLM 4.6 |
| Vibe Code Bench (Vals AI) | 3.1% | Not measured | Only GLM 4.6 measured |
| LiveCodeBench (Artificial Analysis run) | 69.5% | 78.9% | GPT-5 Nano |
| Terminal-Bench Hard (Artificial Analysis run) | 28.8% | 17.4% | GLM 4.6 |
| Terminal-Bench | 24.5% | 21.8% | GLM 4.6 |
| WeirdML | Not measured | 38.1% | Only GPT-5 Nano measured |
| ALE-Bench | 340.8 | Not measured | Only GLM 4.6 measured |
| LMArena Text: coding | 1449 | 1351 | GLM 4.6 |
| LMArena Text: software and IT | 1455 | 1345 | GLM 4.6 |
| LMArena WebDev: HTML | 1350 | Not measured | Only GLM 4.6 measured |
| Neither model has a result on the other 25 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GLM 4.6 | GPT-5 Nano | Leader |
|---|---|---|---|
| AA Intelligence Index | 18.5 | 13.0 | GLM 4.6 |
| Epoch Capabilities Index | Not measured | 139.2 | Only GPT-5 Nano measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GLM 4.6 | GPT-5 Nano | Leader |
|---|---|---|---|
| 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% | 36.5% | GLM 4.6 |
| Neither model has a result on the other 34 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | GLM 4.6 | GPT-5 Nano | Leader |
|---|---|---|---|
| GPQA Diamond | 74.5% | 63.4% | GLM 4.6 |
| MMMU Pro (Vals AI) | Not measured | 70.9% | Only GPT-5 Nano measured |
| GPQA Diamond (Artificial Analysis run) | 78.0% | 67.6% | GLM 4.6 |
| Humanity's Last Exam (Artificial Analysis run) | 14.5% | 9.5% | GLM 4.6 |
| GPQA Diamond (Epoch AI run) | Not measured | 69.4% | Only GPT-5 Nano measured |
| ARC-AGI | Not measured | 20.7% | Only GPT-5 Nano measured |
| ARC-AGI-2 | Not measured | 2.6% | Only GPT-5 Nano measured |
| Chess puzzles | Not measured | 22.0% | Only GPT-5 Nano measured |
| Mystery game puzzles | Not measured | 9.0% | Only GPT-5 Nano measured |
| VPCT | Not measured | 37.2% | Only GPT-5 Nano measured |
| LMArena Text: hard prompts | 1440 | 1328 | GLM 4.6 |
| LMArena Text: expert | 1432 | 1321 | GLM 4.6 |
| LMArena Text: hard prompts in English | 1445 | 1338 | GLM 4.6 |
| LMArena Vision: diagrams | Not measured | 1141 | Only GPT-5 Nano measured |
| LMArena Vision: homework | Not measured | 1157 | Only GPT-5 Nano measured |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | GLM 4.6 | GPT-5 Nano | Leader |
|---|---|---|---|
| AIME | 92.7% | 81.2% | GLM 4.6 |
| MATH 500 (Vals AI) | Not measured | 93.8% | Only GPT-5 Nano measured |
| MGSM (Vals AI) | 89.8% | 89.3% | GLM 4.6 |
| AA Math Index | 86.0 | 83.7 | GLM 4.6 |
| AIME 2025 (Artificial Analysis run) | 86.0% | 83.7% | GLM 4.6 |
| OTIS Mock AIME | Not measured | 81.1% | Only GPT-5 Nano measured |
| FrontierMath, tiers 1 to 3 | Not measured | 20.0% | Only GPT-5 Nano measured |
| FrontierMath, tier 4 | Not measured | 2.4% | Only GPT-5 Nano measured |
| ProofBench | Not measured | 12.0% | Only GPT-5 Nano measured |
| MATH level 5 | Not measured | 95.2% | Only GPT-5 Nano measured |
| LMArena Text: math | 1432 | 1317 | GLM 4.6 |
| LMArena Text: mathematical work | 1447 | 1326 | GLM 4.6 |
| Neither model has a result on the other 1 board here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index72
| Benchmark | GLM 4.6 | GPT-5 Nano | Leader |
|---|---|---|---|
| MMLU Pro | 82.2% | 76.1% | GLM 4.6 |
| LegalBench (Vals AI) | 79.6% | 50.1% | GLM 4.6 |
| CaseLaw (Vals AI) | Not measured | 52.6% | Only GPT-5 Nano measured |
| CorpFin (Vals AI) | 56.8% | Not measured | Only GLM 4.6 measured |
| TaxEval (Vals AI) | 66.2% | 67.4% | GPT-5 Nano |
| MortgageTax (Vals AI) | Not measured | 53.6% | Only GPT-5 Nano measured |
| MedQA (Vals AI) | 92.2% | 93.3% | GPT-5 Nano |
| MedCode (Vals AI) | Not measured | 30.4% | Only GPT-5 Nano measured |
| MMLU Pro (Artificial Analysis run) | 82.9% | 78.0% | GLM 4.6 |
| SimpleQA Verified | Not measured | 11.7% | Only GPT-5 Nano measured |
| LMArena Text: science | 1456 | 1318 | GLM 4.6 |
| LMArena Text: medicine and healthcare | 1455 | 1335 | GLM 4.6 |
| LMArena Text: legal and government | 1448 | 1298 | GLM 4.6 |
| LMArena Text: business and finance | 1416 | 1311 | GLM 4.6 |
| Neither model has a result on the other 3 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | GLM 4.6 | GPT-5 Nano | Leader |
|---|---|---|---|
| Design Arena: websites | 1174 | 1101 | GLM 4.6 |
| Design Arena: UI components | 1147 | 1066 | GLM 4.6 |
| Design Arena: game dev | 1151 | 1045 | GLM 4.6 |
| Design Arena: data viz | 1161 | 1056 | GLM 4.6 |
| Design Arena: 3D | 1129 | 966 | GLM 4.6 |
| Design Arena: all code categories | 1166 | 1084 | 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 index171
| Benchmark | GLM 4.6 | GPT-5 Nano | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 30.4% | Only GPT-5 Nano measured |
| MedScribe (Vals AI) | Not measured | 72.9% | Only GPT-5 Nano measured |
| IFBench | 43.4% | 67.6% | GPT-5 Nano |
| Long context reasoning (AA-LCR) | 54.0% | 45.0% | GLM 4.6 |
| DTBench | Not measured | 62.7% | Only GPT-5 Nano measured |
| LMCA | Not measured | 7.9% | Only GPT-5 Nano measured |
| Fiction.LiveBench | Not measured | 44.4% | Only GPT-5 Nano measured |
| LMArena Text | 1440 | 1320 | GLM 4.6 |
| LMArena Text: instruction following | 1410 | 1306 | GLM 4.6 |
| LMArena Text: creative writing | 1412 | 1249 | GLM 4.6 |
| LMArena Vision | Not measured | 1159 | Only GPT-5 Nano measured |
| LMArena Text: English | 1449 | 1321 | GLM 4.6 |
| LMArena Text: non-English | 1426 | 1313 | GLM 4.6 |
| LMArena Text: Chinese | 1499 | 1356 | GLM 4.6 |
| LMArena Text: German | 1447 | 1327 | GLM 4.6 |
| LMArena Text: Japanese | 1393 | 1227 | GLM 4.6 |
| LMArena Text: Korean | 1400 | 1269 | GLM 4.6 |
| LMArena Text: French | 1459 | Not measured | Only GLM 4.6 measured |
| LMArena Text: Spanish | 1436 | 1360 | GLM 4.6 |
| LMArena Text: Russian | 1418 | 1296 | GLM 4.6 |
| LMArena Text: Polish | 1447 | 1314 | GLM 4.6 |
| LMArena Text: multi-turn | 1427 | 1311 | GLM 4.6 |
| LMArena Text: longer queries | 1422 | 1312 | GLM 4.6 |
| LMArena Text: writing and language | 1415 | 1283 | GLM 4.6 |
| LMArena Text: entertainment and media | 1409 | 1268 | GLM 4.6 |
| LMArena Vision: English | Not measured | 1170 | Only GPT-5 Nano measured |
| LMArena Vision: Chinese | Not measured | 1176 | Only GPT-5 Nano measured |
| LMArena Vision: reading text | Not measured | 1152 | Only GPT-5 Nano measured |
| LMArena Vision: humor | Not measured | 1110 | Only GPT-5 Nano measured |
| Neither model has a result on the other 17 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GLM 4.6 | GPT-5 Nano | 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-5 Nano costs less
Repository review
50K input + 3K output tokens
GPT-5 Nano costs less
Agent loop
200K input + 10K output tokens
GPT-5 Nano 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-5 Nano |
|---|---|---|
| Maker | Z.ai | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | September 30, 2025 | August 7, 2025 |
| Context window | 205K | 400K |
| Input $/Mtok | $0.55 | $0.05 |
| Output $/Mtok | $2.20 | $0.40 |
| Coding index | 52.2 | 34.8 |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | Not computable | $0.109 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GLM 4.6 better than GPT-5 Nano for coding?
Pick GLM 4.6 for coding: it scores 52.2 on the Vibe Coding Index against 34.8 for GPT-5 Nano. Pick GPT-5 Nano when output tokens cost 5.5x less, or when the context window is larger, 400K against 205K tokens.
Which is cheaper, GLM 4.6 or GPT-5 Nano?
GLM 4.6 costs $0.55 per million input tokens and $2.20 per million output tokens; GPT-5 Nano costs $0.05 and $0.40. Cost per solved task is known for GPT-5 Nano only.
Which has the bigger context window, GLM 4.6 or GPT-5 Nano?
GPT-5 Nano, with 400K tokens against 205K.
How many benchmarks is the GLM 4.6 vs GPT-5 Nano comparison based on?
54 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-5 Nano's on 1. Where only one model has a result, the page says so instead of naming a winner.