GLM-5 vs GPT-5.3-Codex
Full profiles: GLM-5 (Zhipu AI) and GPT-5.3-Codex (OpenAI): every benchmark, price and rank.
Updated · Data from 7 sources
As of 29 Oct 2026, GLM-5 and GPT-5.3-Codex are neck and neck on quality (60.2 vs 62.9 on the BenchLeader Index, inside the ±7.8 margin), and GLM-5 is 3.1× cheaper at $1.55 vs $4.81 per 1M tokens blended. GPT-5.3-Codex leads in every category we measure both in. GPT-5.3-Codex streams faster.
Key facts (as of 29 Oct 2026)
- GLM-5 scores 60.2 on the BenchLeader Index and GPT-5.3-Codex scores 62.9 (BenchLeader, 29 Oct 2026).
- GLM-5 costs $1.55 per 1M tokens blended (list price, 29 Oct 2026).
- GPT-5.3-Codex costs $4.81 per 1M tokens blended (list price, 29 Oct 2026).
- GPT-5.3-Codex streams faster than GLM-5 (Artificial Analysis, 7-day median, 29 Oct 2026).
- Of the 11 benchmarks both models have, GPT-5.3-Codex leads 10 (BenchLeader, 29 Oct 2026).
GLM-5 benchmarks 
GPT-5.3-Codex benchmarks Which to pick for…
The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.
| Use case | Pick | Why | Confidence |
|---|---|---|---|
| Coding | GPT-5.3-Codex | 61 vs 59 category score; LiveCodeBench 87.3% vs 81.9% | Medium |
| Agents & tool use | GPT-5.3-Codex | 80 vs 58 category score; Terminal-Bench Hard 53.0% vs 43.2% | High |
| Long documents | GPT-5.3-Codex | 67 vs 63 category score; AA-LCR v1.1 83.3% vs 75.7% | Medium |
| Following instructions | GPT-5.3-Codex | 74 vs 71 category score; IFBench 75.4% vs 72.3% | Medium |
| Lowest cost | GLM-5 | $1.55 vs $4.81 per 1M blended; agentic coding session $0.073 vs $0.161 | – |
| Fastest first answer | Either | 46.9 s (GLM-5 (thinking)) vs 54.4 s (GPT-5.3-Codex (xhigh)) to the first answer token | – |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- GLM-5 (thinking) and GPT-5.3-Codex (xhigh) are neck and neck on quality (60.2 vs 62.9, within the ±7.8 margin).
- GLM-5 (thinking) is stronger in knowledge, maths, reasoning.
- GPT-5.3-Codex (xhigh) is stronger in agents & tools, coding, instruction following, long context, multimodal.
- GLM-5 (thinking) is 3.1× cheaper ($1.55 vs $4.81 per 1M blended).
At a glance
| Spec | GLM-5 | GPT-5.3-Codex |
|---|---|---|
| Developer | Zhipu AI | OpenAI |
| Released | 11 Feb 2026 | 5 Feb 2026 |
| Context window (tokens) | 204,800 | 400,000 |
| Compared at | GLM-5 (thinking) | GPT-5.3-Codex (xhigh) |
| Open weights | Yes | No |
| Price in / out / cached input per 1M | $1.00 / $3.20 / $0.200 | $1.75 / $14.00 / $0.175 |
Category by category
Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.
| Category | GLM-5 (thinking) | GPT-5.3-Codex (xhigh) | Leader |
|---|---|---|---|
| Reasoning | 68.2 | – | not comparable |
| Coding | 59.1 | 60.9 | GPT-5.3-Codex |
| Agents & tools | 58.0 | 80.0 | GPT-5.3-Codex |
| Maths | 63.2 | – | not comparable |
| Knowledge | 57.3 | – | not comparable |
| Instruction following | 70.8 | 73.5 | GPT-5.3-Codex |
| Multimodal | – | 61.2 | not comparable |
| Long context | 62.6 | 66.6 | GPT-5.3-Codex |
Where sources disagree
Across the 11 benchmarks both have, GLM-5 leads 1, GPT-5.3-Codex leads 10.
| Overall index | GLM-5 (thinking) | GPT-5.3-Codex (xhigh) | Leader |
|---|---|---|---|
| BenchLeader Index | 60.2 | 62.9 | neck and neck |
Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).
Price, speed and latency
List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page; suite cost is what Artificial Analysis paid to run its whole Intelligence Index.
| Measure | GLM-5 (thinking) | GPT-5.3-Codex (xhigh) |
|---|---|---|
| Blended price per 1M tokens | $1.55 | $4.81 |
| Input / output per 1M | $1.00 / $3.20 | $1.75 / $14.00 |
| Cached input per 1M | $0.200 | $0.175 |
| Price per task: chat reply | $0.0014 | $0.0049 |
| Price per task: summarize a 30-page report | $0.014 | $0.029 |
| Price per task: code edit | $0.011 | $0.032 |
| Price per task: agentic coding session | $0.073 | $0.161 |
| Price per task: structured extraction | $0.0026 | $0.0063 |
| Output speed | 69 tok/s | 80 tok/s |
| Time to first answer | 46.9 s | 54.4 s |
| Time to a complete answer | 54.2 s | 60.6 s |
Each model is compared at its best-ranked reasoning-effort setting. GLM-5 (thinking) scores 60.2 and takes 47 s to its first answer token; GLM-5 scores 54.9 in 2 s. GPT-5.3-Codex (xhigh) scores 62.9 and takes 54 s to its first answer token. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.
Every benchmark
61 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.
| Metric | Publisher | GLM-5 (thinking) | GPT-5.3-Codex (xhigh) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 60.2 | 62.9 |
| Agents & tools score | BenchLeader | 58.0 | 80.0 |
| Coding score | BenchLeader | 59.1 | 60.9 |
| Instruction following score | BenchLeader | 70.8 | 73.5 |
| Knowledge score | BenchLeader | 57.3 | – |
| Long context score | BenchLeader | 62.6 | 66.6 |
| Maths score | BenchLeader | 63.2 | – |
| Reasoning score | BenchLeader | 68.2 | – |
| Multimodal score | BenchLeader | – | 61.2 |
| Blended price $/M | BenchLeader | $1.55 | $4.81 |
| Output speed | BenchLeader | 69 tok/s | 80 tok/s |
| Time to first answer | BenchLeader | 46.9 s | 54.4 s |
| Context window | BenchLeader | 204,800 tokens | 400,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 87.8%† | – |
| SimpleBench | SimpleBench | 53.2%† | – |
| Arena Hard Prompts | Arena (LMArena) | 1478† | – |
| GPQA Diamond (AA) | Artificial Analysis | 82.0% | 91.5% |
| Humanity's Last Exam (AA) | Artificial Analysis | 29.3% | 42.5% |
| GPQA Diamond (Vals) | Vals AI | 83.3% | – |
| Kagi LLM Benchmark | Kagi LLM Benchmark | 75.0% | – |
| ARC-AGI-1 | ARC Prize | 44.7%† | – |
| ARC-AGI-2 | ARC Prize | 4.9%† | – |
| CritPt | Artificial Analysis | 2.0% | 16.9% |
| CL-bench | Epoch AI Benchmarking Hub | 18.7%† | – |
| ForecastBench | ForecastBench | 63.7%† | – |
| Coding | |||
| SWE-bench Verified (Epoch) | Epoch AI Benchmarking Hub | 72.1%† | 74.8%† |
| WeirdML | WeirdML | 48.2%† | 77.9% |
| Arena Coding | Arena (LMArena) | 1498† | – |
| Arena WebDev | Arena (LMArena) | 1436† | 1407† |
| LiveCodeBench | Vals AI | 81.9% | 87.3% |
| IOI | Vals AI | – | 53.8% |
| SWE-bench (Vals) | Vals AI | 71.4% | 78.0% |
| SWE-bench Verified (bash only) | SWE-bench | 72.8%† | – |
| SWE-bench Verified (any scaffold) | SWE-bench | 72.8%† | – |
| Vibe Code Bench v1.1 | Vals AI | 23.4% | 61.8% |
| SWE Atlas: Codebase QnA | Scale AI SEAL | 20.5%† | – |
| SWE Atlas: Refactoring | Scale AI SEAL | 24.2%† | – |
| SWE Atlas: Test Writing | Scale AI SEAL | 28.7%† | – |
Show all 61 benchmarks
| Metric | Publisher | GLM-5 (thinking) | GPT-5.3-Codex (xhigh) |
|---|---|---|---|
| Coding | |||
| ALE-Bench | Epoch AI Benchmarking Hub | 765.6† | 1655.2 |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 52.4%† | 78.4%† |
| Terminal-Bench Hard | Artificial Analysis | 43.2% | 53.0% |
| τ²-Bench Telecom (AA) | Artificial Analysis | 98.3% | 86.0% |
| HiL-Bench | Scale AI SEAL | – | 4.3%† |
| τ²-bench | τ²-bench | 81.0% | – |
| τ³-bench Banking | τ²-bench | 9.8% | – |
| APEX-Agents (AA) | Artificial Analysis | 14.4% | – |
| Terminal-Bench 2.0 (Vals) | Vals AI | 49.4% | 64.0%† |
| METR Time Horizons | METR | – | 74.5%† |
| Vending-Bench 2 | Andon Labs | 4432.1† | 5940.1† |
| AA-Briefcase v1.1 | Artificial Analysis | – | 868 |
| Maths | |||
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 80.0%† | – |
| AIME (Vals) | Vals AI | 91.7% | – |
| AIME 2026 | MathArena | 96.7%† | – |
| HMMT February 2026 | MathArena | 86.4%† | – |
| USAMO 2026 | MathArena | 35.1%† | – |
| MathArena Apex | MathArena | 10.9%† | – |
| Arena Maths | Arena (LMArena) | 1444† | – |
| Knowledge | |||
| MMLU-Pro | Vals AI | 86.0% | – |
| LegalBench | Vals AI | 84.1% | – |
| CorpFin | Vals AI | 62.9% | – |
| TaxEval | Vals AI | 70.0% | – |
| MedQA | Vals AI | 94.3% | – |
| CaseLaw v2 | Vals AI | 52.5% | – |
| Instruction following | |||
| IFBench | Artificial Analysis | 72.3% | 75.4% |
| Arena Instruction Following | Arena (LMArena) | 1447† | – |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1457† | – |
| Arena Creative Writing | Arena (LMArena) | 1448† | – |
| Arena Multi-turn | Arena (LMArena) | 1471† | – |
| Arena Longer Queries | Arena (LMArena) | 1468† | – |
| Multimodal | |||
| MMMU-Pro | Artificial Analysis | – | 78.5% |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 75.7% | 83.3% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 145.8† | 157.1† |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 27.9 | 32.5 |
| AA Progress Index v1 | Artificial Analysis | 280.9 | 301.3 |
Data as of 2026-10-29. Best configuration of each model; every score links to its source on the model pages.
What changed
- GPT-5.3-Codex (xhigh): 1 new result (AA-Briefcase v1.1).
- GLM-5 (thinking): BenchLeader Index 60.6 → 60.1.
- GLM-5 (thinking): 1 new result (AA Progress Index v1); cached input price moved from $0.15/M to $0.20/M (34% up).
- GPT-5.3-Codex (xhigh): 1 new result (AA Progress Index v1).
- GLM-5 (thinking): cached input price moved from $0.20/M to $0.15/M (25% down).
- GLM-5 (thinking): cached input price moved from $0.15/M to $0.20/M (34% up).
- GLM-5 (thinking): cached input price moved from $0.20/M to $0.15/M (25% down).
- GLM-5 (thinking): cached input price moved from $0.15/M to $0.20/M (34% up).
- GLM-5 (thinking): cached input price moved from $0.20/M to $0.15/M (25% down).
- GLM-5 (thinking): 1 new result (τ³-bench Banking).
Related comparisons
- GLM-5 vs Claude Opus 5.5
- GLM-5 vs Gemini 4 Carbon
- GLM-5 vs GPT-6 Astra
- GPT-5.3-Codex vs Claude Opus 5.5
- GPT-5.3-Codex vs Gemini 4 Carbon
- GPT-5.3-Codex vs GPT-6 Astra
- GPT-5.3-Codex vs GPT-6.1 Sol
- GLM-5 vs o3
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
GLM-5 vs GPT-5.3-Codex: questions
- Is GLM-5 better than GPT-5.3-Codex?
- GLM-5 (thinking) and GPT-5.3-Codex (xhigh) are neck and neck on quality (60.2 vs 62.9, within the ±7.8 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 29 Oct 2026, so check the category scores for your use.
- GLM-5 vs GPT-5.3-Codex: which is cheaper, and will that change?
- GLM-5 is cheaper today: $1.55 against $4.81 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is GLM-5 or GPT-5.3-Codex better for coding?
- GPT-5.3-Codex scores higher in coding (61 vs 59 on the category index, where 50 is average). On LiveCodeBench, the top shared coding benchmark, it is 81.9% for GLM-5 against 87.3% for GPT-5.3-Codex.
- Which is faster, GLM-5 or GPT-5.3-Codex?
- GPT-5.3-Codex streams faster (80 vs 69 output tokens per second, Artificial Analysis 7-day median).
- Is GLM-5 or GPT-5.3-Codex better for agents and tool use?
- GPT-5.3-Codex scores higher in agentic tasks (80 vs 58 on the category index, where 50 is average). On Terminal-Bench Hard, the top shared agents & tools benchmark, it is 43.2% for GLM-5 against 53.0% for GPT-5.3-Codex.
More questions (4)
- Which is better for long documents?
- GPT-5.3-Codex scores higher on long-context benchmarks (67 vs 63). GPT-5.3-Codex accepts more context: 400,000 against 204,800 tokens for GLM-5.
- Which has lower latency?
- GLM-5 answers first: 46.9 s against 54.4 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
- Do independent benchmarks agree on GLM-5 vs GPT-5.3-Codex?
- Across the 11 benchmarks both have, GLM-5 leads 1, GPT-5.3-Codex leads 10.
- When was GLM-5 released?
- GLM-5 was released on 11 Feb 2026.