GPT-5.3-Codex vs Kimi K3
Full profiles: GPT-5.3-Codex (OpenAI) and Kimi K3 (Moonshot AI): every benchmark, price and rank.
Updated · Data from 12 sources
As of 2 Nov 2026, GPT-5.3-Codex and Kimi K3 are neck and neck on quality (62.9 vs 62.1 on the BenchLeader Index, inside the ±7.5 margin), and GPT-5.3-Codex is 1.2× cheaper at $4.81 vs $6.00 per 1M tokens blended. Choose GPT-5.3-Codex for agents & tools (80 vs 59), where it also streams ~1.5× faster; choose Kimi K3 for fast first answers (37.2 s vs 64.7 s) and coding (64 vs 61), long context (69 vs 67), and multimodal (63 vs 61).
Key facts (as of 2 Nov 2026)
- GPT-5.3-Codex scores 62.9 on the BenchLeader Index and Kimi K3 scores 62.1 (BenchLeader, 2 Nov 2026).
- GPT-5.3-Codex costs $4.81 per 1M tokens blended (list price, 2 Nov 2026).
- Kimi K3 costs $6.00 per 1M tokens blended (list price, 2 Nov 2026).
- GPT-5.3-Codex streams ~1.5× faster than Kimi K3 (Artificial Analysis, 7-day median, 2 Nov 2026).
- Of the 12 benchmarks both models have, Kimi K3 leads 9 (BenchLeader, 2 Nov 2026).
GPT-5.3-Codex benchmarks 
Kimi K3 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 | Kimi K3 | 64 vs 61 category score; WeirdML 82.6% vs 77.9% | Medium |
| Agents & tool use | GPT-5.3-Codex | 80 vs 59 category score; AA-Briefcase v1.1 868 vs 1498 | High |
| Long documents | Kimi K3 | 69 vs 67 category score; AA-LCR v1.1 88.7% vs 83.3% | Medium |
| Images and other media | Kimi K3 | 63 vs 61 category score; MMMU-Pro 80.5% vs 78.5% | Medium |
| Chat quality (human preference) | – | Only Kimi K3 has an Arena rating (68 category score) | Not comparable |
| Lowest cost | GPT-5.3-Codex | $4.81 vs $6.00 per 1M blended; agentic coding session $0.161 vs $0.240 | – |
| Fastest first answer | Kimi K3 | 37.2 s (Kimi K3 (max)) vs 64.7 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
- GPT-5.3-Codex (xhigh) and Kimi K3 (max) are neck and neck on quality (62.9 vs 62.1, within the ±7.5 margin).
- GPT-5.3-Codex (xhigh) is stronger in agents & tools, instruction following.
- Kimi K3 (max) is stronger in coding, long context, multimodal, human preference, knowledge, maths, reasoning.
- GPT-5.3-Codex (xhigh) is 1.2× cheaper ($4.81 vs $6.00 per 1M blended).
- GPT-5.3-Codex (xhigh) streams 1.7× faster (114 vs 66 tokens per second).
At a glance
| Spec | GPT-5.3-Codex | Kimi K3 |
|---|---|---|
| Developer | OpenAI | Moonshot AI |
| Released | 5 Feb 2026 | 16 Jul 2026 |
| Context window (tokens) | 400,000 | 1,048,576 |
| Compared at | GPT-5.3-Codex (xhigh) | Kimi K3 (max) |
| Open weights | No | Yes |
| Price in / out / cached input per 1M | $1.75 / $14.00 / $0.175 | $3.00 / $15.00 / $0.300 |
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 | GPT-5.3-Codex (xhigh) | Kimi K3 (max) | Leader |
|---|---|---|---|
| Reasoning | – | 60.0 | not comparable |
| Coding | 60.9 | 64.4 | Kimi K3 |
| Agents & tools | 80.0 | 59.2 | GPT-5.3-Codex |
| Maths | – | 63.2 | not comparable |
| Knowledge | – | 59.8 | not comparable |
| Instruction following | 73.5 | – | not comparable |
| Human preference | – | 68.0 | not comparable |
| Multimodal | 61.1 | 63.1 | Kimi K3 |
| Long context | 66.6 | 69.4 | Kimi K3 |
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.
ModelIndex
Where sources disagree
Across the 12 benchmarks both have, GPT-5.3-Codex leads 3, Kimi K3 leads 9.
| Overall index | GPT-5.3-Codex (xhigh) | Kimi K3 (max) | Leader |
|---|---|---|---|
| BenchLeader Index | 62.9 | 62.1 | 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 | GPT-5.3-Codex (xhigh) | Kimi K3 (max) |
|---|---|---|
| Blended price per 1M tokens | $4.81 | $6.00 |
| Input / output per 1M | $1.75 / $14.00 | $3.00 / $15.00 |
| Cached input per 1M | $0.175 | $0.300 |
| Price per task: chat reply | $0.0049 | $0.0057 |
| Price per task: summarize a 30-page report | $0.029 | $0.045 |
| Price per task: code edit | $0.032 | $0.041 |
| Price per task: agentic coding session | $0.161 | $0.240 |
| Price per task: structured extraction | $0.0063 | $0.0090 |
| Agentic coding session, input mostly cached | $0.090 | $0.118 |
| Output speed | 114 tok/s | 66 tok/s |
| Time to first answer | 64.7 s | 37.2 s |
| Time to a complete answer | 69.1 s | 44.8 s |
Each model is compared at its best-ranked reasoning-effort setting. GPT-5.3-Codex (xhigh) scores 62.9 and takes 65 s to its first answer token. Kimi K3 (max) scores 62.1 and takes 37 s to its first answer token; Kimi K3 scores 59.1 in 1 s, Kimi K3 (low) scores 53.8 in 40 s. 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
148 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 | GPT-5.3-Codex (xhigh) | Kimi K3 (max) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 62.9 | 62.1 |
| Agents & tools score | BenchLeader | 80.0 | 59.2 |
| Coding score | BenchLeader | 60.9 | 64.4 |
| Instruction following score | BenchLeader | 73.5 | – |
| Long context score | BenchLeader | 66.6 | 69.4 |
| Multimodal score | BenchLeader | 61.1 | 63.1 |
| Human preference score | BenchLeader | – | 68.0 |
| Knowledge score | BenchLeader | – | 59.8 |
| Maths score | BenchLeader | – | 63.2 |
| Reasoning score | BenchLeader | – | 60.0 |
| Blended price $/M | BenchLeader | $4.81 | $6.00 |
| Output speed | BenchLeader | 114 tok/s | 66 tok/s |
| Time to first answer | BenchLeader | 64.7 s | 37.2 s |
| Context window | BenchLeader | 400,000 tokens | 1,048,576 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | – | 93.1% |
| SimpleBench | SimpleBench | – | 60.7% |
| Arena Hard Prompts | Arena (LMArena) | – | 1517 |
| LiveBench 2.0 Reasoning | LiveBench | – | 90.7%† |
| LiveBench 1.0 Reasoning | LiveBench | – | 90.7%† |
| GPQA Diamond (AA) | Artificial Analysis | 91.5% | 93.5% |
| Humanity's Last Exam (AA) | Artificial Analysis | 42.5% | 46.9% |
| HLE-Diamond (AA) | Artificial Analysis | – | 26.9% |
| GPQA Diamond (Vals) | Vals AI | – | 92.9%† |
| ARC-AGI-1 | ARC Prize | – | 94.5% |
| ARC-AGI-2 | ARC Prize | – | 60.4% |
| CritPt | Artificial Analysis | 16.9% | 23.4% |
| CritPt v2 hard subset (AA) | Artificial Analysis | – | 39.5% |
| Chess Puzzles | Epoch AI Benchmarking Hub | – | 36.0% |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | – | 26.0% |
| LMCA | Epoch AI Benchmarking Hub | – | 52.7% |
| DTBench | Epoch AI Benchmarking Hub | – | 91.2% |
| ForecastBench | ForecastBench | – | 64.7% |
| Coding | |||
| SWE-bench Verified (Epoch) | Epoch AI Benchmarking Hub | 74.8%† | – |
| SciCode | SciCode | – | 59.5% |
| WeirdML | WeirdML | 77.9% | 82.6% |
| FrontierCode | Cognition | – | 44.2%† |
| Arena Coding | Arena (LMArena) | – | 1540 |
| Arena WebDev | Arena (LMArena) | 1407† | 1656 |
| LiveBench 2.0 Coding | LiveBench | – | 59.3%† |
Show all 148 benchmarks
| Metric | Publisher | GPT-5.3-Codex (xhigh) | Kimi K3 (max) |
|---|---|---|---|
| Coding | |||
| LiveBench 1.0 Coding | LiveBench | – | 81.5%† |
| LiveCodeBench | Vals AI | 87.3% | 87.2% |
| IOI | Vals AI | 53.8% | 48.9% |
| SWE-bench (Vals) | Vals AI | 78.0% | 93.4%† |
| Code Migration | Vals AI | – | 16.1% |
| Code Migration v1.1 | Vals AI | – | 28.6% |
| ProgramBench | Vals AI | – | 2.0%† |
| SWE-bench Multimodal | Vals AI | – | 44.2% |
| Vibe Code Bench 1-100 | Vals AI | – | 18.2% |
| Vibe Code Bench v1.1 | Vals AI | 61.8% | 85.0% |
| Surface Evolver Bench | Epoch AI Benchmarking Hub | – | 93.0% |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | – | 68.5% |
| ALE-Bench | Epoch AI Benchmarking Hub | 1655.2 | 1524.5 |
| FrontierSWE | Epoch AI Benchmarking Hub | – | 25.9% |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | – | 12.6% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | – | 85.0% |
| Startrise Frontend | Startrise | – | 79.8%† |
| GameBench 2 Overall | DuelLab GameBench 2 | – | 48.8† |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | – | 45.1 |
| FrontierCode 1.1 (AA) | Artificial Analysis | – | 43.6% |
| FrontierCode 2.0 (AA) | Artificial Analysis | – | 10.9%† |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 78.4%† | – |
| APEX-Agents | Mercor | – | 47.8%† |
| Arena Agent | Arena (LMArena) | – | 1.1 |
| LiveBench Long Agentic | LiveBench | – | 26.4%† |
| LiveBench Browser | LiveBench | – | 75.2%† |
| LiveBench Agentic Coding | LiveBench | – | 62.2%† |
| Terminal-Bench Hard | Artificial Analysis | 53.0% | – |
| τ²-Bench Telecom (AA) | Artificial Analysis | 86.0% | – |
| Terminal-Bench 2.1 (Vals) | Vals AI | – | 80.9%† |
| MCP Atlas | Scale AI SEAL | – | 82.3% |
| HiL-Bench | Scale AI SEAL | 4.3%† | 42.7%† |
| τ³-bench Banking | τ²-bench | – | 37.1% |
| τ³-Banking (AA) | Artificial Analysis | – | 46.0% |
| ITBench SRE (AA) | Artificial Analysis | – | 47.7% |
| Analyst Agent (AA) | Artificial Analysis | – | 38.8% |
| APEX-Agents (AA) | Artificial Analysis | – | 41.3% |
| CyberBench | Vals AI | – | 75.2% |
| Finance Agent v2 | Vals AI | – | 53.1% |
| Finance Agent v2.1 | Vals AI | – | 60.0% |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | – | 12.9% |
| Harvey's Legal Agent Benchmark v1 | Vals AI | – | 12.9% |
| Legal Research Bench | Vals AI | – | 46.1% |
| Tax Agent Bench | Vals AI | – | 33.4% |
| Terminal-Bench 2.0 (Vals) | Vals AI | 64.0%† | – |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 17.2% |
| Terminal-Bench Science | Vals AI | – | 1.4% |
| Time Horizon Index: KSP | Vals AI | – | 10.5% |
| PostTrainBench | Epoch AI Benchmarking Hub | – | 32.0%† |
| METR Time Horizons | METR | 74.5%† | – |
| GBAEval | Epoch AI Benchmarking Hub | – | 48.4%† |
| Vending-Bench 2 | Andon Labs | 5940.1† | 5165.0† |
| AutomationBench | Artificial Analysis | – | 58.3% |
| GDP.pdf (AA) | Artificial Analysis | – | 22.0% |
| Harvey LAB-AA v1.1 | Harvey | – | 5.3% |
| EnterpriseOps-Gym | Artificial Analysis | – | 45.3% |
| AA-Briefcase v1.1 | Artificial Analysis | 868 | 1498 |
| GDPx | GDPx by SemiAnalysis | – | 3.7% |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | – | 8.1% |
| CWE-Bench (AA) | Artificial Analysis | – | 53.3% |
| DeepSec-Bench (AA) | Artificial Analysis | – | 12.4% |
| CyberGym end-to-end (AA) | Artificial Analysis | – | 58.0% |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | – | 72.2% |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | – | 39.0% |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | – | 97.2% |
| ProofBench | Vals AI | – | 87.0%† |
| LiveBench Mathematics | LiveBench | – | 84.4%† |
| AIME 2026 | MathArena | – | 96.7%† |
| HMMT February 2026 | MathArena | – | 97.0%† |
| MathArena Apex | MathArena | – | 65.6%† |
| Arena Maths | Arena (LMArena) | – | 1499 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | – | 50.6% |
| LiveBench 2.0 Data Analysis | LiveBench | – | 78.7%† |
| LiveBench Research | LiveBench | – | 79.0%† |
| LiveBench 1.0 Data Analysis | LiveBench | – | 78.7%† |
| AA-Omniscience v1.1 | Artificial Analysis | – | -1.7† |
| MMLU-Pro | Vals AI | – | 88.0% |
| LegalBench | Vals AI | – | 86.2% |
| CorpFin | Vals AI | – | 71.6%† |
| TaxEval | Vals AI | – | 75.7%† |
| BioMysteryBench | Vals AI | – | 72.6% |
| Excel Modeling Benchmark | Vals AI | – | 66.7% |
| Excel Modeling Benchmark v1.1 | Vals AI | – | 71.3% |
| MedCode | Vals AI | – | 49.4% |
| MedScribe | Vals AI | – | 88.0% |
| Public Benefits Bench v1.1 | Vals AI | – | 68.2% |
| GDP.pdf | Epoch AI Benchmarking Hub | – | 19.0% |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | – | 42.4%† |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | – | 23.4%† |
| HealthBench Professional (AA) | OpenAI | – | 53.2% |
| Instruction following | |||
| LiveBench Language | LiveBench | – | 85.5%† |
| LiveBench Instruction Following | LiveBench | – | 71.4%† |
| IFBench | Artificial Analysis | 75.4% | – |
| Arena Instruction Following | Arena (LMArena) | – | 1490 |
| Human preference | |||
| Arena Text | Arena (LMArena) | – | 1488 |
| EQ-Bench 4 | EQ-Bench | – | 1319† |
| Arena Creative Writing | Arena (LMArena) | – | 1463 |
| Arena Multi-turn | Arena (LMArena) | – | 1502 |
| Arena Longer Queries | Arena (LMArena) | – | 1503 |
| Multimodal | |||
| LiveBench Design | LiveBench | – | 77.2%† |
| MMMU-Pro | Artificial Analysis | 78.5% | 80.5% |
| MMMU-Pro (Vals) | Vals AI | – | 88.2%† |
| MortgageTax | Vals AI | – | 66.3%† |
| SAGE | Vals AI | – | 86.8% |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | – | 29.5%† |
| Code2Video-AA | Artificial Analysis | – | 1041 |
| AA-3D | Artificial Analysis | – | 982 |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 83.3% | 88.7% |
| MLCR | Artificial Analysis | – | 21.7% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | – | 158.3† |
| LiveBench 2.0 | LiveBench | – | 64.6%† |
| LiveBench 1.0 | LiveBench | – | 79.2%† |
| AA Intelligence Index v5.0 | Artificial Analysis | – | 17.4† |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 32.5 | 43.6 |
| AA Progress Index v1 | Artificial Analysis | 301.3 | 319.9 |
| Vals Index | Vals AI | – | 53.0 |
| Vals Finance Index | Vals AI | – | 58.0% |
| Vals RSI Index | Vals AI | – | 20.9% |
| Vals Multimodal Index | Vals AI | – | 73.4%† |
| Vals Router Index | Vals AI | – | 53.0%† |
| AA Cyber Index | Artificial Analysis | – | 41.3 |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | – | 26.6% |
| Metadata | |||
| AA Openness Index | Artificial Analysis | – | 38.9 |
Data as of 2026-11-02. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261026-cb69502a12d9 (https://benchmarks.duellab.org/releases/gb2-20261026-cb69502a12d9/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- Kimi K3 (max): 1 new result (MirrorCode).
- GPT-5.3-Codex (xhigh): 1 new result (AA-Briefcase v1.1).
- Kimi K3 (max): 1 score revision.
- Kimi K3 (max): BenchLeader Index 63.1 → 62.1.
- GPT-5.3-Codex (xhigh): 1 new result (AA Progress Index v1).
- Kimi K3 (max): 3 new results (AA Progress Index v1, HLE-Diamond (AA), CritPt v2 hard subset (AA)); 1 score revision.
- Kimi K3 (max): 7 new results (Code Migration v1.1, Excel Modeling Benchmark v1.1, Finance Agent v2.1…).
- Kimi K3 (max): 1 new result (Terminal-Bench-Science 0.1 (AA)); 1 score revision.
- Kimi K3 (max): 3 score revisions.
- Kimi K3 (max): 1 score revision.
Related comparisons
- 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
- Kimi K3 vs Claude Opus 5.5
- Kimi K3 vs Gemini 4 Carbon
- Kimi K3 vs GPT-6 Astra
- Kimi K3 vs GPT-6.1 Sol
- GPT-5.3-Codex vs Claude Fable 5.1
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
GPT-5.3-Codex vs Kimi K3: questions
- Is GPT-5.3-Codex better than Kimi K3?
- GPT-5.3-Codex (xhigh) and Kimi K3 (max) are neck and neck on quality (62.9 vs 62.1, within the ±7.5 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 2 Nov 2026, so check the category scores for your use.
- GPT-5.3-Codex vs Kimi K3: which is cheaper, and will that change?
- GPT-5.3-Codex is cheaper today: $4.81 against $6.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is GPT-5.3-Codex or Kimi K3 better for coding?
- Kimi K3 scores higher in coding (64 vs 61 on the category index, where 50 is average). On LiveCodeBench, the top shared coding benchmark, it is 87.3% for GPT-5.3-Codex against 87.2% for Kimi K3.
- Which is faster, GPT-5.3-Codex or Kimi K3?
- GPT-5.3-Codex streams ~1.5× faster (114 vs 66 output tokens per second, Artificial Analysis 7-day median).
- Is GPT-5.3-Codex or Kimi K3 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?
- Kimi K3 scores higher on long-context benchmarks (69 vs 67). Kimi K3 accepts more context: 1,048,576 against 400,000 tokens for GPT-5.3-Codex.
- Which has lower latency?
- Kimi K3 answers first: 37.2 s against 64.7 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 GPT-5.3-Codex vs Kimi K3?
- Across the 12 benchmarks both have, GPT-5.3-Codex leads 3, Kimi K3 leads 9.
- When was Kimi K3 released?
- Kimi K3 was released on 16 Jul 2026.