Ministral 3 14B (Reasoning) vs Claude 3 Haiku

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

Ministral 3 14B (Reasoning) is clearly ahead on the aggregate, 60 to 49. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Ministral 3 14B (Reasoning)'s sharpest advantage is in coding, where it averages 35 against 19.3. The single biggest benchmark swing on the page is SWE-bench Verified, 39 to 17.

Ministral 3 14B (Reasoning) is the reasoning model in the pair, while Claude 3 Haiku 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. Claude 3 Haiku gives you the larger context window at 200K, compared with 128K for Ministral 3 14B (Reasoning).

Quick Verdict

Pick Ministral 3 14B (Reasoning) if you want the stronger benchmark profile. Claude 3 Haiku only becomes the better choice if you need the larger 200K context window or you would rather avoid the extra latency and token burn of a reasoning model.

Agentic

Ministral 3 14B (Reasoning)

Ministral 3 14B (Reasoning)

58.5

Claude 3 Haiku

44

60
Terminal-Bench 2.0
40
61
BrowseComp
53
55
OSWorld-Verified
42

Coding

Ministral 3 14B (Reasoning)

Ministral 3 14B (Reasoning)

35

Claude 3 Haiku

19.3

62
HumanEval
48
39
SWE-bench Verified
17
33
LiveCodeBench
20
36
SWE-bench Pro
19

Multimodal & Grounded

Ministral 3 14B (Reasoning)

Ministral 3 14B (Reasoning)

71.5

Claude 3 Haiku

68.7

71
MMMU-Pro
70
72
OfficeQA Pro
67

Reasoning

Ministral 3 14B (Reasoning)

Ministral 3 14B (Reasoning)

69.2

Claude 3 Haiku

59.6

70
SimpleQA
54
70
MuSR
52
80
BBH
74
66
LongBench v2
63
66
MRCRv2
63

Knowledge

Ministral 3 14B (Reasoning)

Ministral 3 14B (Reasoning)

52.1

Claude 3 Haiku

42.8

71
MMLU
56
70
GPQA
56
68
SuperGPQA
54
66
OpenBookQA
52
69
MMLU-Pro
63
7
HLE
2
62
FrontierScience
50

Instruction Following

Ministral 3 14B (Reasoning)

Ministral 3 14B (Reasoning)

81

Claude 3 Haiku

76

81
IFEval
76

Multilingual

Ministral 3 14B (Reasoning)

Ministral 3 14B (Reasoning)

77.8

Claude 3 Haiku

71.1

81
MGSM
73
76
MMLU-ProX
70

Mathematics

Ministral 3 14B (Reasoning)

Ministral 3 14B (Reasoning)

75.2

Claude 3 Haiku

62.2

73
AIME 2023
56
75
AIME 2024
58
74
AIME 2025
57
69
HMMT Feb 2023
52
71
HMMT Feb 2024
54
70
HMMT Feb 2025
53
72
BRUMO 2025
55
79
MATH-500
71

Frequently Asked Questions

Which is better, Ministral 3 14B (Reasoning) or Claude 3 Haiku?

Ministral 3 14B (Reasoning) is ahead overall, 60 to 49. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 39 and 17.

Which is better for knowledge tasks, Ministral 3 14B (Reasoning) or Claude 3 Haiku?

Ministral 3 14B (Reasoning) has the edge for knowledge tasks in this comparison, averaging 52.1 versus 42.8. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Ministral 3 14B (Reasoning) or Claude 3 Haiku?

Ministral 3 14B (Reasoning) has the edge for coding in this comparison, averaging 35 versus 19.3. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Which is better for math, Ministral 3 14B (Reasoning) or Claude 3 Haiku?

Ministral 3 14B (Reasoning) has the edge for math in this comparison, averaging 75.2 versus 62.2. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Ministral 3 14B (Reasoning) or Claude 3 Haiku?

Ministral 3 14B (Reasoning) has the edge for reasoning in this comparison, averaging 69.2 versus 59.6. Inside this category, MuSR is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Ministral 3 14B (Reasoning) or Claude 3 Haiku?

Ministral 3 14B (Reasoning) has the edge for agentic tasks in this comparison, averaging 58.5 versus 44. 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, Ministral 3 14B (Reasoning) or Claude 3 Haiku?

Ministral 3 14B (Reasoning) has the edge for multimodal and grounded tasks in this comparison, averaging 71.5 versus 68.7. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Ministral 3 14B (Reasoning) or Claude 3 Haiku?

Ministral 3 14B (Reasoning) has the edge for instruction following in this comparison, averaging 81 versus 76. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Ministral 3 14B (Reasoning) or Claude 3 Haiku?

Ministral 3 14B (Reasoning) has the edge for multilingual tasks in this comparison, averaging 77.8 versus 71.1. 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.