GPT-5.3 Codex vs Ministral 3 14B

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

GPT-5.3 Codex is clearly ahead on the aggregate, 89 to 55. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-5.3 Codex's sharpest advantage is in coding, where it averages 87.3 against 33. The single biggest benchmark swing on the page is SWE-bench Pro, 90 to 34.

GPT-5.3 Codex is also the more expensive model on tokens at $2.50 input / $10.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Ministral 3 14B. That is roughly Infinityx on output cost alone. GPT-5.3 Codex is the reasoning model in the pair, while Ministral 3 14B 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 gives you the larger context window at 400K, compared with 128K for Ministral 3 14B.

Quick Verdict

Pick GPT-5.3 Codex if you want the stronger benchmark profile. Ministral 3 14B 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

GPT-5.3 Codex

88.1

Ministral 3 14B

48.4

90
Terminal-Bench 2.0
48
88
BrowseComp
55
86
OSWorld-Verified
44

Coding

GPT-5.3 Codex

GPT-5.3 Codex

87.3

Ministral 3 14B

33

95
HumanEval
58
85
SWE-bench Verified
37
85
LiveCodeBench
31
90
SWE-bench Pro
34

Multimodal & Grounded

GPT-5.3 Codex

GPT-5.3 Codex

91.3

Ministral 3 14B

70.5

89
MMMU-Pro
70
94
OfficeQA Pro
71

Reasoning

GPT-5.3 Codex

GPT-5.3 Codex

93.7

Ministral 3 14B

63.6

95
SimpleQA
66
93
MuSR
64
98
BBH
74
92
LongBench v2
60
93
MRCRv2
60

Knowledge

GPT-5.3 Codex

GPT-5.3 Codex

80.3

Ministral 3 14B

50.1

99
MMLU
69
97
GPQA
68
95
SuperGPQA
66
93
OpenBookQA
64
90
MMLU-Pro
67
44
HLE
5
90
FrontierScience
60

Instruction Following

GPT-5.3 Codex

GPT-5.3 Codex

93

Ministral 3 14B

80

93
IFEval
80

Multilingual

GPT-5.3 Codex

GPT-5.3 Codex

92.8

Ministral 3 14B

76.8

96
MGSM
80
91
MMLU-ProX
75

Mathematics

GPT-5.3 Codex

GPT-5.3 Codex

97.7

Ministral 3 14B

69.7

99
AIME 2023
68
99
AIME 2024
70
98
AIME 2025
72
95
HMMT Feb 2023
64
97
HMMT Feb 2024
66
96
HMMT Feb 2025
65
96
BRUMO 2025
67
99
MATH-500
72

Frequently Asked Questions

Which is better, GPT-5.3 Codex or Ministral 3 14B?

GPT-5.3 Codex is ahead overall, 89 to 55. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 90 and 34.

Which is better for knowledge tasks, GPT-5.3 Codex or Ministral 3 14B?

GPT-5.3 Codex has the edge for knowledge tasks in this comparison, averaging 80.3 versus 50.1. Inside this category, HLE is the benchmark that creates the most daylight between them.

Which is better for coding, GPT-5.3 Codex or Ministral 3 14B?

GPT-5.3 Codex has the edge for coding in this comparison, averaging 87.3 versus 33. 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 or Ministral 3 14B?

GPT-5.3 Codex has the edge for math in this comparison, averaging 97.7 versus 69.7. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, GPT-5.3 Codex or Ministral 3 14B?

GPT-5.3 Codex has the edge for reasoning in this comparison, averaging 93.7 versus 63.6. Inside this category, MRCRv2 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GPT-5.3 Codex or Ministral 3 14B?

GPT-5.3 Codex has the edge for agentic tasks in this comparison, averaging 88.1 versus 48.4. 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 or Ministral 3 14B?

GPT-5.3 Codex has the edge for multimodal and grounded tasks in this comparison, averaging 91.3 versus 70.5. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, GPT-5.3 Codex or Ministral 3 14B?

GPT-5.3 Codex has the edge for instruction following in this comparison, averaging 93 versus 80. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, GPT-5.3 Codex or Ministral 3 14B?

GPT-5.3 Codex has the edge for multilingual tasks in this comparison, averaging 92.8 versus 76.8. 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.