GPT-5.2 Instant vs Claude Haiku 4.5

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

GPT-5.2 Instant is clearly ahead on the aggregate, 85 to 62. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-5.2 Instant's sharpest advantage is in coding, where it averages 75.5 against 41.7. The single biggest benchmark swing on the page is LiveCodeBench, 74 to 36.

GPT-5.2 Instant is also the more expensive model on tokens at $1.50 input / $6.00 output per 1M tokens, versus $0.80 input / $4.00 output per 1M tokens for Claude Haiku 4.5. GPT-5.2 Instant is the reasoning model in the pair, while Claude Haiku 4.5 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 Haiku 4.5 gives you the larger context window at 200K, compared with 128K for GPT-5.2 Instant.

Quick Verdict

Pick GPT-5.2 Instant if you want the stronger benchmark profile. Claude Haiku 4.5 only becomes the better choice if you want the cheaper token bill or you need the larger 200K context window.

Agentic

GPT-5.2 Instant

GPT-5.2 Instant

79.6

Claude Haiku 4.5

56.7

83
Terminal-Bench 2.0
53
82
BrowseComp
62
74
OSWorld-Verified
57

Coding

GPT-5.2 Instant

GPT-5.2 Instant

75.5

Claude Haiku 4.5

41.7

87
HumanEval
60
75
SWE-bench Verified
48
74
LiveCodeBench
36
77
SWE-bench Pro
46

Multimodal & Grounded

GPT-5.2 Instant

GPT-5.2 Instant

93.1

Claude Haiku 4.5

78.4

94
MMMU-Pro
82
92
OfficeQA Pro
74

Reasoning

GPT-5.2 Instant

GPT-5.2 Instant

90.9

Claude Haiku 4.5

68.9

95
SimpleQA
65
93
MuSR
63
96
BBH
81
89
LongBench v2
72
84
MRCRv2
70

Knowledge

GPT-5.2 Instant

GPT-5.2 Instant

79.8

Claude Haiku 4.5

53.6

98
MMLU
68
97
GPQA
67
95
SuperGPQA
65
93
OpenBookQA
63
88
MMLU-Pro
73
43
HLE
11
91
FrontierScience
64

Instruction Following

GPT-5.2 Instant

GPT-5.2 Instant

95

Claude Haiku 4.5

86

95
IFEval
86

Multilingual

GPT-5.2 Instant

GPT-5.2 Instant

94.4

Claude Haiku 4.5

80.1

95
MGSM
82
94
MMLU-ProX
79

Mathematics

GPT-5.2 Instant

GPT-5.2 Instant

97.2

Claude Haiku 4.5

73.3

99
AIME 2023
68
99
AIME 2024
70
98
AIME 2025
69
95
HMMT Feb 2023
64
97
HMMT Feb 2024
66
96
HMMT Feb 2025
65
96
BRUMO 2025
67
98
MATH-500
81

Frequently Asked Questions

Which is better, GPT-5.2 Instant or Claude Haiku 4.5?

GPT-5.2 Instant is ahead overall, 85 to 62. The biggest single separator in this matchup is LiveCodeBench, where the scores are 74 and 36.

Which is better for knowledge tasks, GPT-5.2 Instant or Claude Haiku 4.5?

GPT-5.2 Instant has the edge for knowledge tasks in this comparison, averaging 79.8 versus 53.6. Inside this category, HLE is the benchmark that creates the most daylight between them.

Which is better for coding, GPT-5.2 Instant or Claude Haiku 4.5?

GPT-5.2 Instant has the edge for coding in this comparison, averaging 75.5 versus 41.7. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.

Which is better for math, GPT-5.2 Instant or Claude Haiku 4.5?

GPT-5.2 Instant has the edge for math in this comparison, averaging 97.2 versus 73.3. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, GPT-5.2 Instant or Claude Haiku 4.5?

GPT-5.2 Instant has the edge for reasoning in this comparison, averaging 90.9 versus 68.9. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GPT-5.2 Instant or Claude Haiku 4.5?

GPT-5.2 Instant has the edge for agentic tasks in this comparison, averaging 79.6 versus 56.7. 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 Instant or Claude Haiku 4.5?

GPT-5.2 Instant has the edge for multimodal and grounded tasks in this comparison, averaging 93.1 versus 78.4. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, GPT-5.2 Instant or Claude Haiku 4.5?

GPT-5.2 Instant has the edge for instruction following in this comparison, averaging 95 versus 86. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, GPT-5.2 Instant or Claude Haiku 4.5?

GPT-5.2 Instant has the edge for multilingual tasks in this comparison, averaging 94.4 versus 80.1. 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.