GPT-5.3-Codex-Spark vs Kimi K2.5

Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.

GPT-5.3-Codex-Spark is clearly ahead on the aggregate, 87 to 60. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-5.3-Codex-Spark's sharpest advantage is in coding, where it averages 82.3 against 38.9. The single biggest benchmark swing on the page is SWE-bench Pro, 85 to 40.

GPT-5.3-Codex-Spark is also the more expensive model on tokens at $2.00 input / $8.00 output per 1M tokens, versus $0.50 input / $2.80 output per 1M tokens for Kimi K2.5. That is roughly 2.9x on output cost alone. GPT-5.3-Codex-Spark is the reasoning model in the pair, while Kimi K2.5 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. GPT-5.3-Codex-Spark gives you the larger context window at 256K, compared with 128K for Kimi K2.5.

Quick Verdict

Pick GPT-5.3-Codex-Spark if you want the stronger benchmark profile. Kimi K2.5 only becomes the better choice if you want the cheaper token bill or you would rather avoid the extra latency and token burn of a reasoning model.

Agentic

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

85.6

Kimi K2.5

52.3

90
Terminal-Bench 2.0
51
82
BrowseComp
59
83
OSWorld-Verified
49

Coding

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

82.3

Kimi K2.5

38.9

91
HumanEval
69
80
SWE-bench Verified
42
80
LiveCodeBench
37
85
SWE-bench Pro
40

Multimodal & Grounded

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

88.3

Kimi K2.5

64.6

86
MMMU-Pro
61
91
OfficeQA Pro
69

Reasoning

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

92.7

Kimi K2.5

71.7

94
SimpleQA
74
92
MuSR
72
97
BBH
81
91
LongBench v2
67
92
MRCRv2
70

Knowledge

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

78.3

Kimi K2.5

57.2

97
MMLU
77
95
GPQA
76
93
SuperGPQA
74
91
OpenBookQA
72
88
MMLU-Pro
74
42
HLE
11
88
FrontierScience
67

Instruction Following

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

92

Kimi K2.5

85

92
IFEval
85

Multilingual

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

90.8

Kimi K2.5

79.8

94
MGSM
83
89
MMLU-ProX
78

Mathematics

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

96.7

Kimi K2.5

78.7

98
AIME 2023
77
98
AIME 2024
79
97
AIME 2025
78
94
HMMT Feb 2023
73
96
HMMT Feb 2024
75
95
HMMT Feb 2025
74
95
BRUMO 2025
76
98
MATH-500
82

Frequently Asked Questions

Which is better, GPT-5.3-Codex-Spark or Kimi K2.5?

GPT-5.3-Codex-Spark is ahead overall, 87 to 60. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 85 and 40.

Which is better for knowledge tasks, GPT-5.3-Codex-Spark or Kimi K2.5?

GPT-5.3-Codex-Spark has the edge for knowledge tasks in this comparison, averaging 78.3 versus 57.2. Inside this category, HLE is the benchmark that creates the most daylight between them.

Which is better for coding, GPT-5.3-Codex-Spark or Kimi K2.5?

GPT-5.3-Codex-Spark has the edge for coding in this comparison, averaging 82.3 versus 38.9. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for math, GPT-5.3-Codex-Spark or Kimi K2.5?

GPT-5.3-Codex-Spark has the edge for math in this comparison, averaging 96.7 versus 78.7. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, GPT-5.3-Codex-Spark or Kimi K2.5?

GPT-5.3-Codex-Spark has the edge for reasoning in this comparison, averaging 92.7 versus 71.7. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GPT-5.3-Codex-Spark or Kimi K2.5?

GPT-5.3-Codex-Spark has the edge for agentic tasks in this comparison, averaging 85.6 versus 52.3. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, GPT-5.3-Codex-Spark or Kimi K2.5?

GPT-5.3-Codex-Spark has the edge for multimodal and grounded tasks in this comparison, averaging 88.3 versus 64.6. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, GPT-5.3-Codex-Spark or Kimi K2.5?

GPT-5.3-Codex-Spark has the edge for instruction following in this comparison, averaging 92 versus 85. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, GPT-5.3-Codex-Spark or Kimi K2.5?

GPT-5.3-Codex-Spark has the edge for multilingual tasks in this comparison, averaging 90.8 versus 79.8. Inside this category, MGSM is the benchmark that creates the most daylight between them.

Last updated: March 12, 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.