GLM 4.5 Air vs GPT-5.1-Codex-Max
GLM 4.5 Air costs 9.1x less per output token than GPT-5.1-Codex-Max ($1.10 vs $10.00 per million). Updated October 21, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- No data
- Output $/M
- $1.10
- Coding
- No data
- Overall
- No data
- Output $/M
- $10.00
GLM 4.5 Air or GPT-5.1-Codex-Max: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick GLM 4.5 Air for output tokens 9.1x cheaper ($1.10 vs $10.00 per million).
No benchmark has tested both yet. GLM 4.5 Air has results on LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run) and GSO-Bench; GPT-5.1-Codex-Max on LiveCodeBench (Vals AI), Vibe Code Bench (Vals AI) and Terminal-Bench. Compare them on price and context instead.
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, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
No call
Only GLM 4.5 Air has a AA Intelligence Index result, 11.1.
Directional only
Web design
Design Arena: websites
No call
Only GLM 4.5 Air has a Design Arena: websites result, 1146.
Directional only
Long documents
Listed context window
GPT-5.1-Codex-Max
GPT-5.1-Codex-Max takes 400K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GLM 4.5 Air
GLM 4.5 Air $0.0008, GPT-5.1-Codex-Max $0.0063 per turn.
List prices
At a glance
- Coding index
- GLM 4.5 Air not benchmarked, GPT-5.1-Codex-Max not benchmarked.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- GLM 4.5 Air $1.10 against GPT-5.1-Codex-Max $10.00 per million output tokens, 9.1x apart.
- Context window
- GLM 4.5 Air takes 131K tokens, GPT-5.1-Codex-Max 400K.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
CodingDirectional onlySix of these boards feed the Vibe Coding Index9 boards measured
| Benchmark | GLM 4.5 Air | GPT-5.1-Codex-Max | Leader |
|---|---|---|---|
| LiveCodeBench (Vals AI) | Not measured | 83.6% | Only GPT-5.1-Codex-Max measured |
| Vibe Code Bench (Vals AI) | Not measured | 22.2% | Only GPT-5.1-Codex-Max measured |
| LiveCodeBench (Artificial Analysis run) | 68.4% | Not measured | Only GLM 4.5 Air measured |
| Terminal-Bench Hard (Artificial Analysis run) | 20.5% | Not measured | Only GLM 4.5 Air measured |
| Terminal-Bench | Not measured | 60.4% | Only GPT-5.1-Codex-Max measured |
| GSO-Bench | 2.9% | Not measured | Only GLM 4.5 Air measured |
| ALE-Bench | Not measured | 1228.3 | Only GPT-5.1-Codex-Max measured |
| LMArena Text: coding | 1397 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: software and IT | 1401 | Not measured | Only GLM 4.5 Air measured |
| Neither model has a result on the other 30 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | GLM 4.5 Air | GPT-5.1-Codex-Max | Leader |
|---|---|---|---|
| AA Intelligence Index | 11.1 | Not measured | Only GLM 4.5 Air measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | GLM 4.5 Air | GPT-5.1-Codex-Max | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 46.5% | Not measured | Only GLM 4.5 Air measured |
| METR time horizons | Not measured | 70.8% | Only GPT-5.1-Codex-Max measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index6 boards measured
| Benchmark | GLM 4.5 Air | GPT-5.1-Codex-Max | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 73.3% | Not measured | Only GLM 4.5 Air measured |
| Humanity's Last Exam (Artificial Analysis run) | 7.0% | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: hard prompts | 1379 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: expert | 1370 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: hard prompts in English | 1388 | Not measured | Only GLM 4.5 Air measured |
| Kagi LLM Benchmark | 43.0% | Not measured | Only GLM 4.5 Air measured |
| Neither model has a result on the other 16 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index5 boards measured
| Benchmark | GLM 4.5 Air | GPT-5.1-Codex-Max | Leader |
|---|---|---|---|
| AA Math Index | 80.7 | Not measured | Only GLM 4.5 Air measured |
| AIME 2025 (Artificial Analysis run) | 80.7% | Not measured | Only GLM 4.5 Air measured |
| ProofBench | Not measured | 9.0% | Only GPT-5.1-Codex-Max measured |
| LMArena Text: math | 1396 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: mathematical work | 1396 | Not measured | Only GLM 4.5 Air measured |
| Neither model has a result on the other 8 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index5 boards measured
| Benchmark | GLM 4.5 Air | GPT-5.1-Codex-Max | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 81.5% | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: science | 1407 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: medicine and healthcare | 1402 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: legal and government | 1382 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: business and finance | 1371 | Not measured | Only GLM 4.5 Air measured |
| Neither model has a result on the other 13 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards measured
| Benchmark | GLM 4.5 Air | GPT-5.1-Codex-Max | Leader |
|---|---|---|---|
| Design Arena: websites | 1146 | Not measured | Only GLM 4.5 Air measured |
| Design Arena: UI components | 1123 | Not measured | Only GLM 4.5 Air measured |
| Design Arena: game dev | 1094 | Not measured | Only GLM 4.5 Air measured |
| Design Arena: data viz | 1186 | Not measured | Only GLM 4.5 Air measured |
| Design Arena: 3D | 1123 | Not measured | Only GLM 4.5 Air measured |
| Design Arena: all code categories | 1137 | Not measured | Only GLM 4.5 Air measured |
| Design Arena: SVG | 1071 | Not measured | Only GLM 4.5 Air measured |
| Neither model has a result on the other 2 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index19 boards measured
| Benchmark | GLM 4.5 Air | GPT-5.1-Codex-Max | Leader |
|---|---|---|---|
| IFBench | 37.6% | Not measured | Only GLM 4.5 Air measured |
| Long context reasoning (AA-LCR) | 46.7% | Not measured | Only GLM 4.5 Air measured |
| LMArena Text | 1384 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: instruction following | 1354 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: creative writing | 1343 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: English | 1397 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: non-English | 1366 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: Chinese | 1426 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: German | 1377 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: Japanese | 1348 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: Korean | 1308 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: French | 1400 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: Spanish | 1385 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: Russian | 1373 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: Polish | 1368 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: multi-turn | 1371 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: longer queries | 1366 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: writing and language | 1354 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: entertainment and media | 1339 | Not measured | Only GLM 4.5 Air measured |
| Neither model has a result on the other 27 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
GLM 4.5 Air costs less
Repository review
50K input + 3K output tokens
GLM 4.5 Air costs less
Agent loop
200K input + 10K output tokens
GLM 4.5 Air 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 4.5 Air | OpenAI GPT-5.1-Codex-Max |
|---|---|---|
| Maker | Z.ai | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | July 25, 2025 | December 4, 2025 |
| Context window | 131K | 400K |
| Input $/Mtok | $0.20 | $1.25 |
| Output $/Mtok | $1.10 | $10.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GLM 4.5 Air better than GPT-5.1-Codex-Max for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GLM 4.5 Air for output tokens 9.1x cheaper ($1.10 vs $10.00 per million).
Which is cheaper, GLM 4.5 Air or GPT-5.1-Codex-Max?
GLM 4.5 Air costs $0.20 per million input tokens and $1.10 per million output tokens; GPT-5.1-Codex-Max costs $1.25 and $10.00. Cost per solved task is known for neither of them.
Which has the bigger context window, GLM 4.5 Air or GPT-5.1-Codex-Max?
GPT-5.1-Codex-Max, with 400K tokens against 131K.
Has any benchmark tested both GLM 4.5 Air and GPT-5.1-Codex-Max?
No benchmark has tested both yet. GLM 4.5 Air has results on LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run) and GSO-Bench; GPT-5.1-Codex-Max on LiveCodeBench (Vals AI), Vibe Code Bench (Vals AI) and Terminal-Bench. Compare them on price and context instead. Data as of October 21, 2026.