GPT-5.2 Pro vs Claude 3 Haiku

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

GPT-5.2 Pro is clearly ahead on the aggregate, 90 to 49. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-5.2 Pro's sharpest advantage is in coding, where it averages 84.8 against 19.3. The single biggest benchmark swing on the page is SWE-bench Pro, 89 to 19.

GPT-5.2 Pro 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. GPT-5.2 Pro gives you the larger context window at 400K, compared with 200K for Claude 3 Haiku.

Quick Verdict

Pick GPT-5.2 Pro if you want the stronger benchmark profile. Claude 3 Haiku only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.

Agentic

GPT-5.2 Pro

GPT-5.2 Pro

85.9

Claude 3 Haiku

44

88
Terminal-Bench 2.0
40
88
BrowseComp
53
82
OSWorld-Verified
42

Coding

GPT-5.2 Pro

GPT-5.2 Pro

84.8

Claude 3 Haiku

19.3

93
HumanEval
48
83
SWE-bench Verified
17
81
LiveCodeBench
20
89
SWE-bench Pro
19

Multimodal & Grounded

GPT-5.2 Pro

GPT-5.2 Pro

96

Claude 3 Haiku

68.7

96
MMMU-Pro
70
96
OfficeQA Pro
67

Reasoning

GPT-5.2 Pro

GPT-5.2 Pro

95.2

Claude 3 Haiku

59.6

97
SimpleQA
54
95
MuSR
52
98
BBH
74
93
LongBench v2
63
95
MRCRv2
63

Knowledge

GPT-5.2 Pro

GPT-5.2 Pro

81.5

Claude 3 Haiku

42.8

99
MMLU
56
99
GPQA
56
97
SuperGPQA
54
95
OpenBookQA
52
90
MMLU-Pro
63
44
HLE
2
93
FrontierScience
50

Instruction Following

GPT-5.2 Pro

GPT-5.2 Pro

95

Claude 3 Haiku

76

95
IFEval
76

Multilingual

GPT-5.2 Pro

GPT-5.2 Pro

93.4

Claude 3 Haiku

71.1

96
MGSM
73
92
MMLU-ProX
70

Mathematics

GPT-5.2 Pro

GPT-5.2 Pro

98.2

Claude 3 Haiku

62.2

99
AIME 2023
56
99
AIME 2024
58
99
AIME 2025
57
96
HMMT Feb 2023
52
98
HMMT Feb 2024
54
97
HMMT Feb 2025
53
97
BRUMO 2025
55
99
MATH-500
71

Frequently Asked Questions

Which is better, GPT-5.2 Pro or Claude 3 Haiku?

GPT-5.2 Pro is ahead overall, 90 to 49. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 89 and 19.

Which is better for knowledge tasks, GPT-5.2 Pro or Claude 3 Haiku?

GPT-5.2 Pro has the edge for knowledge tasks in this comparison, averaging 81.5 versus 42.8. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, GPT-5.2 Pro or Claude 3 Haiku?

GPT-5.2 Pro has the edge for coding in this comparison, averaging 84.8 versus 19.3. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for math, GPT-5.2 Pro or Claude 3 Haiku?

GPT-5.2 Pro has the edge for math in this comparison, averaging 98.2 versus 62.2. Inside this category, HMMT Feb 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, GPT-5.2 Pro or Claude 3 Haiku?

GPT-5.2 Pro has the edge for reasoning in this comparison, averaging 95.2 versus 59.6. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GPT-5.2 Pro or Claude 3 Haiku?

GPT-5.2 Pro has the edge for agentic tasks in this comparison, averaging 85.9 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, GPT-5.2 Pro or Claude 3 Haiku?

GPT-5.2 Pro has the edge for multimodal and grounded tasks in this comparison, averaging 96 versus 68.7. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, GPT-5.2 Pro or Claude 3 Haiku?

GPT-5.2 Pro has the edge for instruction following in this comparison, averaging 95 versus 76. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, GPT-5.2 Pro or Claude 3 Haiku?

GPT-5.2 Pro has the edge for multilingual tasks in this comparison, averaging 93.4 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.