GLM 5.3 Flash vs GPT-5.3-Codex
Full profiles: GLM 5.3 Flash (Zhipu AI) and GPT-5.3-Codex (OpenAI): every benchmark, price and rank.
Updated · Data from 11 sources
As of 16 Nov 2026, GLM 5.3 Flash and GPT-5.3-Codex are neck and neck on quality (57.8 vs 62.9 on the BenchLeader Index, inside the ±8.4 margin), and GLM 5.3 Flash is 20× cheaper at $0.238 vs $4.81 per 1M tokens blended. Choose GLM 5.3 Flash for multimodal (64 vs 61); choose GPT-5.3-Codex for fast first answers (38.2 s vs 87.0 s) and agents & tools (80 vs 59), coding (61 vs 57), and long context (66 vs 65), where it also streams ~1.5× faster.
Key facts (as of 16 Nov 2026)
- GLM 5.3 Flash scores 57.8 on the BenchLeader Index and GPT-5.3-Codex scores 62.9 (BenchLeader, 16 Nov 2026).
- GLM 5.3 Flash costs $0.238 per 1M tokens blended (list price, 16 Nov 2026).
- GPT-5.3-Codex costs $4.81 per 1M tokens blended (list price, 16 Nov 2026).
- GPT-5.3-Codex streams ~1.5× faster than GLM 5.3 Flash (Artificial Analysis, 7-day median, 16 Nov 2026).
- Of the 6 benchmarks both models have, GPT-5.3-Codex leads 4 (BenchLeader, 16 Nov 2026).
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 57 category score | Medium |
| Agents & tool use | GPT-5.3-Codex | 80 vs 59 category score; AA-Briefcase v1.1 868 vs 1450 | High |
| Long documents | GPT-5.3-Codex | 66 vs 65 category score; AA-LCR v1.1 83.3% vs 80.0% | Medium |
| Images and other media | GLM 5.3 Flash | 64 vs 61 category score | Medium |
| Chat quality (human preference) | – | Only GLM 5.3 Flash has an Arena rating (66 category score) | Not comparable |
| Lowest cost | GLM 5.3 Flash | $0.238 vs $4.81 per 1M blended; agentic coding session $0.011 vs $0.161 | – |
| Fastest first answer | GPT-5.3-Codex | 38.2 s (GPT-5.3-Codex (xhigh)) vs 87.0 s (GLM 5.3 Flash) 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 5.3 Flash and GPT-5.3-Codex (xhigh) are neck and neck on quality (57.8 vs 62.9, within the ±8.4 margin).
- GLM 5.3 Flash is stronger in multimodal.
- GPT-5.3-Codex (xhigh) is stronger in agents & tools, coding, long context.
- GLM 5.3 Flash is 20× cheaper ($0.238 vs $4.81 per 1M blended).
- GPT-5.3-Codex (xhigh) streams 1.7× faster (94 vs 54 tokens per second).
At a glance
| Spec | GLM 5.3 Flash | GPT-5.3-Codex |
|---|---|---|
| Developer | Zhipu AI | OpenAI |
| Released | 20 Aug 2026 | 5 Feb 2026 |
| Context window (tokens) | 1,000,000 | 400,000 |
| Compared at | GLM 5.3 Flash | GPT-5.3-Codex (xhigh) |
| Open weights | Yes | No |
| Price in / out / cached input per 1M | $0.150 / $0.500 / $0.030 | $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 5.3 Flash | GPT-5.3-Codex (xhigh) | Leader |
|---|---|---|---|
| Reasoning | 48.3 | – | not comparable |
| Coding | 56.9 | 61.0 | GPT-5.3-Codex |
| Agents & tools | 58.7 | 80.1 | GPT-5.3-Codex |
| Maths | 68.8 | – | not comparable |
| Knowledge | 45.1 | – | not comparable |
| Instruction following | – | 73.6 | not comparable |
| Human preference | 66.4 | – | not comparable |
| Multimodal | 64.0 | 60.8 | GLM 5.3 Flash |
| Long context | 64.6 | 66.4 | GPT-5.3-Codex |
On one chart
Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.
Not drawn, measured for fewer than two of these models: Reasoning, Maths, Knowledge, Instruction following, Human preference.
Where sources disagree
Across the 6 benchmarks both have, GLM 5.3 Flash leads 2, GPT-5.3-Codex leads 4.
| Overall index | GLM 5.3 Flash | GPT-5.3-Codex (xhigh) | Leader |
|---|---|---|---|
| BenchLeader Index | 57.8 | 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. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.
| Measure | GLM 5.3 Flash | GPT-5.3-Codex (xhigh) |
|---|---|---|
| Blended price per 1M tokens | $0.238 | $4.81 |
| Input / output per 1M | $0.150 / $0.500 | $1.75 / $14.00 |
| Cached input per 1M | $0.030 | $0.175 |
| Price per task: chat reply | $0.0002 | $0.0049 |
| Price per task: summarize a 30-page report | $0.0021 | $0.029 |
| Price per task: code edit | $0.0017 | $0.032 |
| Price per task: agentic coding session | $0.011 | $0.161 |
| Price per task: structured extraction | $0.0004 | $0.0063 |
| Agentic coding session, input mostly cached | $0.0056 | $0.090 |
| Cost per benchmark task (AA Index) | $0.583 | – |
| Output tokens per task (AA Index) | 134k | – |
| Of which reasoning | 103k | – |
| Time per task (AA Index) | 41 min | – |
| Output speed | 54 tok/s | 94 tok/s |
| Time to first answer | 87.0 s | 38.2 s |
| Time to a complete answer, last measured 13 Nov 2026 | 220.4 s | 97.1 s |
Each model is compared at its best-ranked reasoning-effort setting. GLM 5.3 Flash scores 57.8 and takes 87 s to its first answer token; GLM 5.3 Flash (max) scores 52.4 in 87 s. GPT-5.3-Codex (xhigh) scores 62.9 and takes 38 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
144 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 5.3 Flash | GPT-5.3-Codex (xhigh) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 57.8 | 62.9 |
| Agents & tools score | BenchLeader | 58.7 | 80.1 |
| Coding score | BenchLeader | 56.9 | 61.0 |
| Human preference score | BenchLeader | 66.4 | – |
| Knowledge score | BenchLeader | 45.1 | – |
| Long context score | BenchLeader | 64.6 | 66.4 |
| Maths score | BenchLeader | 68.8 | – |
| Multimodal score | BenchLeader | 64.0 | 60.8 |
| Reasoning score | BenchLeader | 48.3 | – |
| Instruction following score | BenchLeader | – | 73.6 |
| Blended price $/M | BenchLeader | $0.238 | $4.81 |
| Output speed | BenchLeader | 54 tok/s | 94 tok/s |
| Time to first answer | BenchLeader | 87.0 s | 38.2 s |
| Context window | BenchLeader | 1,000,000 tokens | 400,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 90.2%† | – |
| Arena Hard Prompts | Arena (LMArena) | 1500 | – |
| LiveBench 2.0 Reasoning | LiveBench | 77.6%† | – |
| LiveBench 1.0 Reasoning | LiveBench | 77.6% | – |
| GPQA Diamond (AA) | Artificial Analysis | 91.2% | 91.5% |
| Humanity's Last Exam (AA) | Artificial Analysis | 39.9% | 42.5% |
| HLE-Diamond (AA) | Artificial Analysis | 18.2% | – |
| GPQA Diamond (Vals) | Vals AI | 86.4%† | – |
| ARC-AGI-1 | ARC Prize | 91.0%† | – |
| ARC-AGI-2 | ARC Prize | 65.8%† | – |
| CritPt | Artificial Analysis | 15.4% | 16.9% |
| CritPt v2 hard subset (AA) | Artificial Analysis | 24.5% | – |
| Arena Expert | Arena (LMArena) | 1511 | – |
| Chess Puzzles | Epoch AI Benchmarking Hub | 21.0%† | – |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 8.0%† | – |
| BTF-3 | Epoch AI Benchmarking Hub | 14.9% | – |
| Coding | |||
| SWE-bench Verified (Epoch) | Epoch AI Benchmarking Hub | – | 74.8%† |
| SciCode | SciCode | 51.6% | – |
| WeirdML | WeirdML | – | 77.9% |
| FrontierCode | Cognition | 31.8%† | – |
| Arena Coding | Arena (LMArena) | 1526 | – |
| Arena WebDev | Arena (LMArena) | 1609 | 1406† |
| LiveBench 2.0 Coding | LiveBench | 70.9%† | – |
| LiveBench 1.0 Coding | LiveBench | 79.0% | – |
| LiveCodeBench | Vals AI | 80.5%† | 87.3% |
Show all 144 benchmarks
| Metric | Publisher | GLM 5.3 Flash | GPT-5.3-Codex (xhigh) |
|---|---|---|---|
| Coding | |||
| IOI | Vals AI | 52.5%† | 53.8% |
| SWE-bench (Vals) | Vals AI | 92.0%† | 78.0% |
| Code Migration | Vals AI | 20.5%† | – |
| Code Migration v1.1 | Vals AI | 51.6%† | – |
| ProgramBench | Vals AI | 0.0%† | – |
| Vibe Code Bench 1-100 | Vals AI | 16.0%† | – |
| Vibe Code Bench v1.1 | Vals AI | 30.8%† | 61.8% |
| SWE Atlas v1.1 | Scale AI SEAL | 55.3% | – |
| SWE Atlas v1.1: Codebase QnA | Scale AI SEAL | 66.9% | – |
| SWE Atlas v1.1: Test Writing | Scale AI SEAL | 53.3% | – |
| SWE Atlas v1.1: Refactoring | Scale AI SEAL | 45.7% | – |
| Surface Evolver Bench | Epoch AI Benchmarking Hub | 52.5%† | – |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | 63.4%† | – |
| CursorBench | Cursor | 36.8%† | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 303.6† | 1655.2 |
| FrontierSWE | Epoch AI Benchmarking Hub | 18.1%† | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 32.8% | – |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 84.3% | – |
| GameBench 2 Overall | DuelLab GameBench 2 | 54.9 | – |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | 57.2† | – |
| Design Arena Website | Design Arena | 1257 | 1155† |
| FrontierCode 1.1 (AA) | Artificial Analysis | 41.0% | – |
| FrontierCode 2.0 (AA) | Artificial Analysis | 17.6% | – |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 37.0%† | 78.4%† |
| APEX-Agents | Mercor | 52.8% | – |
| Arena Agent | Arena (LMArena) | -2.9 | – |
| LiveBench Long Agentic | LiveBench | 20.7%† | – |
| LiveBench Browser | LiveBench | 59.8%† | – |
| LiveBench Agentic Coding | LiveBench | 56.8% | – |
| Terminal-Bench Hard | Artificial Analysis | – | 53.0% |
| τ²-Bench Telecom (AA) | Artificial Analysis | – | 86.0% |
| Terminal-Bench 2.1 (Vals) | Vals AI | 62.9%† | – |
| HiL-Bench | Scale AI SEAL | – | 4.3%† |
| GDPval-AA v2.1, normalised score | Artificial Analysis | 57.1% | – |
| GDPval-AA v2.1 | Artificial Analysis | 1648 | – |
| τ³-Banking (AA) | Artificial Analysis | 47.2% | – |
| ITBench SRE (AA) | Artificial Analysis | 51.2% | – |
| Analyst Agent (AA) | Artificial Analysis | 25.0% | – |
| CyberBench | Vals AI | 67.9%† | – |
| Finance Agent v2 | Vals AI | 57.9%† | – |
| Finance Agent v2.1 | Vals AI | 60.6%† | – |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 10.4%† | – |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 6.7%† | – |
| Legal Research Bench | Vals AI | 45.2%† | – |
| SkillsBench | Vals AI | 40.2%† | – |
| SREBench | Vals AI | 0.8%† | – |
| Tax Agent Bench | Vals AI | 31.6%† | – |
| Terminal-Bench 2.0 (Vals) | Vals AI | – | 64.0%† |
| Terminal-Bench 4.0 (Vals) | Vals AI | 37.4%† | – |
| Terminal-Bench Science | Vals AI | 2.9%† | – |
| Arena Agent Task Completion | Arena (LMArena) | 1.3 | – |
| PostTrainBench | Epoch AI Benchmarking Hub | 36.8%† | – |
| METR Time Horizons | METR | – | 74.5%† |
| Vending-Bench 2 | Andon Labs | – | 5940.1† |
| AutomationBench | Artificial Analysis | 60.4% | – |
| GDP.pdf (AA) | Artificial Analysis | 15.4% | – |
| Harvey LAB-AA v1.1 | Harvey | 0.8% | – |
| EnterpriseOps-Gym | Artificial Analysis | 33.2% | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1450 | 868 |
| Design Arena Agentic | Design Arena | – | 1018† |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 4.8% | – |
| CWE-Bench (AA) | Artificial Analysis | 55.8% | – |
| DeepSec-Bench (AA) | Artificial Analysis | 19.9% | – |
| CyberGym end-to-end (AA) | Artificial Analysis | 74.0% | – |
| MKA (AA) | Artificial Analysis | 36.2% | – |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 55.8%† | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 17.1%† | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 93.9%† | – |
| ProofBench | Vals AI | 21.0%† | – |
| LiveBench Mathematics | LiveBench | 81.2% | – |
| Arena Maths | Arena (LMArena) | 1505 | – |
| Knowledge | |||
| LiveBench 2.0 Data Analysis | LiveBench | 76.4%† | – |
| LiveBench Research | LiveBench | 73.9%† | – |
| LiveBench 1.0 Data Analysis | LiveBench | 76.4% | – |
| AA-Omniscience v1.1 | Artificial Analysis | 0.7 | – |
| MMLU-Pro | Vals AI | 86.1%† | – |
| LegalBench | Vals AI | 83.9%† | – |
| TaxEval | Vals AI | 75.6%† | – |
| Excel Modeling Benchmark | Vals AI | 55.9%† | – |
| Excel Modeling Benchmark v1.1 | Vals AI | 66.3%† | – |
| MedScribe | Vals AI | 88.9%† | – |
| Access to Justice Benchmark | Vals AI | 71.1%† | – |
| GDP.pdf | Epoch AI Benchmarking Hub | 14.0%† | – |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 28.2% | – |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 61.6% | – |
| Instruction following | |||
| LiveBench Language | LiveBench | 77.3% | – |
| LiveBench Instruction Following | LiveBench | 52.8% | – |
| IFBench | Artificial Analysis | – | 75.4% |
| Arena Instruction Following | Arena (LMArena) | 1474 | – |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1475 | – |
| Arena Creative Writing | Arena (LMArena) | 1435 | – |
| Arena Multi-turn | Arena (LMArena) | 1476 | – |
| Arena Longer Queries | Arena (LMArena) | 1480 | – |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1295 | – |
| LiveBench Design | LiveBench | 73.7%† | – |
| MMMU-Pro | Artificial Analysis | – | 78.5% |
| MMMU-Pro (Vals) | Vals AI | 86.0%† | – |
| SAGE | Vals AI | 89.3%† | – |
| Humanity's Sixth Sense | Scale AI SEAL | 26.8%† | – |
| VIALS-AA | Handshake AI | 39.8% | – |
| Code2Video-AA | Artificial Analysis | 975 | – |
| AA-3D | Artificial Analysis | 937 | – |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 80.0% | 83.3% |
| MLCR | Artificial Analysis | 11.7% | – |
| FACTS Grounding | 56.1% | – | |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 153.8 | – |
| LiveBench 2.0 | LiveBench | 60.7%† | – |
| LiveBench 1.0 | LiveBench | 71.6% | – |
| AA Intelligence Index v5.0.1 | Artificial Analysis | 27.8 | – |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 41.8 | 32.5 |
| AA Progress Index v1 | Artificial Analysis | 318.6 | 301.3 |
| Vals Index | Vals AI | 50.9† | – |
| Vals Finance Index | Vals AI | 55.8%† | – |
| Vals Router Index | Vals AI | 50.9% | – |
| Vals Legal Index | Vals AI | 71.0%† | – |
| AA Cyber Index | Artificial Analysis | 49.9 | – |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 26.7% | – |
| DistressBench | Scale AI SEAL | 72.7% | – |
| Metadata | |||
| AA Openness Index | Artificial Analysis | 44.4 | – |
Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- GLM 5.3 Flash: BenchLeader Index 56.7 → 57.8.
- GLM 5.3 Flash: 1 score revision.
- GLM 5.3 Flash: 5 score revisions.
- GLM 5.3 Flash: 1 new result (FORTRESS).
- GLM 5.3 Flash: 2 score revisions; GLM 5.3 Flash cached input price moved from $0.034/M to $0.030/M (13% down).
- GLM 5.3 Flash: GLM 5.3 Flash cached input price moved from $0.030/M to $0.034/M (15% up).
- GLM 5.3 Flash: GLM 5.3 Flash cached input price moved from $0.034/M to $0.030/M (13% down).
- GLM 5.3 Flash: GLM 5.3 Flash cached input price moved from $0.030/M to $0.034/M (15% up).
- GLM 5.3 Flash: BenchLeader Index 57.6 → 56.7.
- GLM 5.3 Flash: 2 new results (AA Intelligence Index v5.0.1, FrontierCode 2.0 (AA)).
Related comparisons
- GLM 5.3 Flash vs Claude Opus 5.5
- GLM 5.3 Flash vs GPT-6.1 Sol
- GLM 5.3 Flash vs Gemini 4 Argon
- GPT-5.3-Codex vs Claude Fable 5.2
- GPT-5.3-Codex vs Gemini 4 Carbon
- GPT-5.3-Codex vs Claude Opus 5.5
- GPT-5.3-Codex vs GPT-6 Astra
- GLM 5.3 vs GPT-5.3-Codex
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
GLM 5.3 Flash vs GPT-5.3-Codex: questions
- Is GLM 5.3 Flash better than GPT-5.3-Codex?
- GLM 5.3 Flash and GPT-5.3-Codex (xhigh) are neck and neck on quality (57.8 vs 62.9, within the ±8.4 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
- GLM 5.3 Flash vs GPT-5.3-Codex: which is cheaper, and will that change?
- GLM 5.3 Flash is cheaper today: $0.238 against $4.81 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is GLM 5.3 Flash or GPT-5.3-Codex better for coding?
- GPT-5.3-Codex scores higher in coding (61 vs 57 on the category index, where 50 is average).
- Which is faster, GLM 5.3 Flash or GPT-5.3-Codex?
- GPT-5.3-Codex streams ~1.5× faster (94 vs 54 output tokens per second, Artificial Analysis 7-day median).
- Is GLM 5.3 Flash or GPT-5.3-Codex better for agents and tool use?
- GPT-5.3-Codex scores higher in agentic tasks (80 vs 59 on the category index, where 50 is average).
More questions (4)
- Which is better for long documents?
- GPT-5.3-Codex scores higher on long-context benchmarks (66 vs 65). GLM 5.3 Flash accepts more context: 1,000,000 against 400,000 tokens for GPT-5.3-Codex.
- Which has lower latency?
- GPT-5.3-Codex answers first: 38.2 s against 87.0 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 5.3 Flash vs GPT-5.3-Codex?
- Across the 6 benchmarks both have, GLM 5.3 Flash leads 2, GPT-5.3-Codex leads 4.
- When was GLM 5.3 Flash released?
- GLM 5.3 Flash was released on 20 Aug 2026.