Claude Haiku 4.5 vs Ministral 3 14B

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

Claude Haiku 4.5 is clearly ahead on the aggregate, 62 to 55. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Claude Haiku 4.5's sharpest advantage is in coding, where it averages 41.7 against 33. The single biggest benchmark swing on the page is OSWorld-Verified, 57 to 44.

Claude Haiku 4.5 is also the more expensive model on tokens at $0.80 input / $4.00 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. Claude Haiku 4.5 gives you the larger context window at 200K, compared with 128K for Ministral 3 14B.

Quick Verdict

Pick Claude Haiku 4.5 if you want the stronger benchmark profile. Ministral 3 14B only becomes the better choice if you want the cheaper token bill.

Agentic

Claude Haiku 4.5

Claude Haiku 4.5

56.7

Ministral 3 14B

48.4

53
Terminal-Bench 2.0
48
62
BrowseComp
55
57
OSWorld-Verified
44

Coding

Claude Haiku 4.5

Claude Haiku 4.5

41.7

Ministral 3 14B

33

60
HumanEval
58
48
SWE-bench Verified
37
36
LiveCodeBench
31
46
SWE-bench Pro
34

Multimodal & Grounded

Claude Haiku 4.5

Claude Haiku 4.5

78.4

Ministral 3 14B

70.5

82
MMMU-Pro
70
74
OfficeQA Pro
71

Reasoning

Claude Haiku 4.5

Claude Haiku 4.5

68.9

Ministral 3 14B

63.6

65
SimpleQA
66
63
MuSR
64
81
BBH
74
72
LongBench v2
60
70
MRCRv2
60

Knowledge

Claude Haiku 4.5

Claude Haiku 4.5

53.6

Ministral 3 14B

50.1

68
MMLU
69
67
GPQA
68
65
SuperGPQA
66
63
OpenBookQA
64
73
MMLU-Pro
67
11
HLE
5
64
FrontierScience
60

Instruction Following

Claude Haiku 4.5

Claude Haiku 4.5

86

Ministral 3 14B

80

86
IFEval
80

Multilingual

Claude Haiku 4.5

Claude Haiku 4.5

80.1

Ministral 3 14B

76.8

82
MGSM
80
79
MMLU-ProX
75

Mathematics

Claude Haiku 4.5

Claude Haiku 4.5

73.3

Ministral 3 14B

69.7

68
AIME 2023
68
70
AIME 2024
70
69
AIME 2025
72
64
HMMT Feb 2023
64
66
HMMT Feb 2024
66
65
HMMT Feb 2025
65
67
BRUMO 2025
67
81
MATH-500
72

Frequently Asked Questions

Which is better, Claude Haiku 4.5 or Ministral 3 14B?

Claude Haiku 4.5 is ahead overall, 62 to 55. The biggest single separator in this matchup is OSWorld-Verified, where the scores are 57 and 44.

Which is better for knowledge tasks, Claude Haiku 4.5 or Ministral 3 14B?

Claude Haiku 4.5 has the edge for knowledge tasks in this comparison, averaging 53.6 versus 50.1. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.

Which is better for coding, Claude Haiku 4.5 or Ministral 3 14B?

Claude Haiku 4.5 has the edge for coding in this comparison, averaging 41.7 versus 33. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for math, Claude Haiku 4.5 or Ministral 3 14B?

Claude Haiku 4.5 has the edge for math in this comparison, averaging 73.3 versus 69.7. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Claude Haiku 4.5 or Ministral 3 14B?

Claude Haiku 4.5 has the edge for reasoning in this comparison, averaging 68.9 versus 63.6. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Claude Haiku 4.5 or Ministral 3 14B?

Claude Haiku 4.5 has the edge for agentic tasks in this comparison, averaging 56.7 versus 48.4. Inside this category, OSWorld-Verified is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Claude Haiku 4.5 or Ministral 3 14B?

Claude Haiku 4.5 has the edge for multimodal and grounded tasks in this comparison, averaging 78.4 versus 70.5. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Claude Haiku 4.5 or Ministral 3 14B?

Claude Haiku 4.5 has the edge for instruction following in this comparison, averaging 86 versus 80. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Claude Haiku 4.5 or Ministral 3 14B?

Claude Haiku 4.5 has the edge for multilingual tasks in this comparison, averaging 80.1 versus 76.8. Inside this category, MMLU-ProX 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.