GPT-5.4 vs Kimi K3
As of Oct 14, 2026, GPT-5.4 leads Kimi K3 in 2 of 7 shared categories: Science and Factuality.
GPT-5.4
It used to be. Was SOTA in General LLM.
Kimi K3
Yes. Yes on General LLM (open weights); Reasoning (open weights). Not the overall leader.
| Category | GPT-5.4 | Kimi K3 |
|---|---|---|
| General LLM | #28 · Was SOTA · General LLM Margin 19.04761904761905 LMArena leaderboard dataset · Oct 13, 2026 | #13 · #13 in General LLM Margin 8.84353741496598 LMArena leaderboard dataset · Oct 13, 2026 |
| Reasoning | #29 · #29 in Reasoning Margin 20.54794520547945 LMArena leaderboard dataset · Oct 13, 2026 | #7 · #7 in Reasoning Margin 5.479452054794521 LMArena leaderboard dataset · Oct 13, 2026 |
| Math | #9 · #9 in Math Margin 17.777777777777757 Epoch AI benchmarking hub · Mar 5, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 |
| Science | #16 · #16 in Science Margin — Epoch AI benchmarking hub · Mar 5, 2026 | #17 · #17 in Science Margin — Epoch AI benchmarking hub · Jul 16, 2026 |
| Coding | #— · Not enough data Margin — Epoch AI benchmarking hub · Mar 5, 2026 | #— · Not enough data Margin — Scale Labs leaderboards · Oct 14, 2026 |
| Coding › Web dev | #55 · #55 in Coding › Web dev Margin 50.467289719626166 LMArena leaderboard dataset · Oct 13, 2026 | #11 · Was SOTA · Coding › Web dev Margin 9.34579439252336 LMArena leaderboard dataset · Oct 13, 2026 |
| Long context | #34 · #34 in Long context Margin 23.12925170068027 LMArena leaderboard dataset · Oct 13, 2026 | #8 · Was SOTA · Long context Margin 5.442176870748298 LMArena leaderboard dataset · Oct 13, 2026 |
| Vision | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 9, 2026 | #22 · #22 in Vision Margin 60.526315789473685 Epoch AI benchmarking hub · Jul 16, 2026 |
| Factuality | #6 · Was SOTA · Factuality Margin 5.22388059701494 LMArena leaderboard dataset · Oct 13, 2026 | #19 · #19 in Factuality Margin 14.925373134328368 LMArena leaderboard dataset · Oct 13, 2026 |
| Abstraction (ARC) | #10 · #10 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Mar 5, 2026 | #8 · #8 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Jul 16, 2026 |
GPT-5.4: $5.625 per 1M blended tokens.
Kimi K3: $4.125 per 1M blended tokens.
GPT-5.4: closed weights.
Kimi K3: open weights.
General LLM: As of Oct 14, 2026, Kimi K3 leads GPT-5.4 in General LLM at #13 against #28.
Reasoning: As of Oct 14, 2026, Kimi K3 leads GPT-5.4 in Reasoning at #7 against #29.
Science: As of Oct 14, 2026, GPT-5.4 leads Kimi K3 in Science at #16 against #17.
Coding › Web dev: As of Oct 14, 2026, Kimi K3 leads GPT-5.4 in Coding › Web dev at #11 against #55.
Long context: As of Oct 14, 2026, Kimi K3 leads GPT-5.4 in Long context at #8 against #34.
Factuality: As of Oct 14, 2026, GPT-5.4 leads Kimi K3 in Factuality at #6 against #19.
Abstraction (ARC): As of Oct 14, 2026, Kimi K3 leads GPT-5.4 in Abstraction (ARC) at #8 against #10.
GPT-5.4 or Kimi K3?
As of Oct 14, 2026, GPT-5.4 leads Kimi K3 in 2 of 7 shared categories: Science and Factuality.
GPT-5.4 or Kimi K3 for General LLM?
As of Oct 14, 2026, Kimi K3 leads GPT-5.4 in General LLM at #13 against #28.
GPT-5.4 or Kimi K3 for Reasoning?
As of Oct 14, 2026, Kimi K3 leads GPT-5.4 in Reasoning at #7 against #29.
GPT-5.4 or Kimi K3 for Science?
As of Oct 14, 2026, GPT-5.4 leads Kimi K3 in Science at #16 against #17.