GPT-5.3-Codex-Spark vs Ministral 3 14B (Reasoning)

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 35. The single biggest benchmark swing on the page is SWE-bench Pro, 85 to 36.

GPT-5.3-Codex-Spark is also the more expensive model on tokens at $2.00 input / $8.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Ministral 3 14B (Reasoning). That is roughly Infinityx on output cost alone. GPT-5.3-Codex-Spark gives you the larger context window at 256K, compared with 128K for Ministral 3 14B (Reasoning).

Quick Verdict

Pick GPT-5.3-Codex-Spark if you want the stronger benchmark profile. Ministral 3 14B (Reasoning) only becomes the better choice if you want the cheaper token bill.

Agentic

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

85.6

Ministral 3 14B (Reasoning)

58.5

90
Terminal-Bench 2.0
60
82
BrowseComp
61
83
OSWorld-Verified
55

Coding

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

82.3

Ministral 3 14B (Reasoning)

35

91
HumanEval
62
80
SWE-bench Verified
39
80
LiveCodeBench
33
85
SWE-bench Pro
36

Multimodal & Grounded

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

88.3

Ministral 3 14B (Reasoning)

71.5

86
MMMU-Pro
71
91
OfficeQA Pro
72

Reasoning

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

92.7

Ministral 3 14B (Reasoning)

69.2

94
SimpleQA
70
92
MuSR
70
97
BBH
80
91
LongBench v2
66
92
MRCRv2
66

Knowledge

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

78.3

Ministral 3 14B (Reasoning)

52.1

97
MMLU
71
95
GPQA
70
93
SuperGPQA
68
91
OpenBookQA
66
88
MMLU-Pro
69
42
HLE
7
88
FrontierScience
62

Instruction Following

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

92

Ministral 3 14B (Reasoning)

81

92
IFEval
81

Multilingual

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

90.8

Ministral 3 14B (Reasoning)

77.8

94
MGSM
81
89
MMLU-ProX
76

Mathematics

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

96.7

Ministral 3 14B (Reasoning)

75.2

98
AIME 2023
73
98
AIME 2024
75
97
AIME 2025
74
94
HMMT Feb 2023
69
96
HMMT Feb 2024
71
95
HMMT Feb 2025
70
95
BRUMO 2025
72
98
MATH-500
79

Frequently Asked Questions

Which is better, GPT-5.3-Codex-Spark or Ministral 3 14B (Reasoning)?

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 36.

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

GPT-5.3-Codex-Spark has the edge for knowledge tasks in this comparison, averaging 78.3 versus 52.1. 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 Ministral 3 14B (Reasoning)?

GPT-5.3-Codex-Spark has the edge for coding in this comparison, averaging 82.3 versus 35. 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 Ministral 3 14B (Reasoning)?

GPT-5.3-Codex-Spark has the edge for math in this comparison, averaging 96.7 versus 75.2. 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 Ministral 3 14B (Reasoning)?

GPT-5.3-Codex-Spark has the edge for reasoning in this comparison, averaging 92.7 versus 69.2. Inside this category, MRCRv2 is the benchmark that creates the most daylight between them.

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

GPT-5.3-Codex-Spark has the edge for agentic tasks in this comparison, averaging 85.6 versus 58.5. 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 Ministral 3 14B (Reasoning)?

GPT-5.3-Codex-Spark has the edge for multimodal and grounded tasks in this comparison, averaging 88.3 versus 71.5. 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-Spark or Ministral 3 14B (Reasoning)?

GPT-5.3-Codex-Spark has the edge for instruction following in this comparison, averaging 92 versus 81. 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 Ministral 3 14B (Reasoning)?

GPT-5.3-Codex-Spark has the edge for multilingual tasks in this comparison, averaging 90.8 versus 77.8. 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.