Claude Haiku 4.5 vs GPT-5 nano

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

Claude Haiku 4.5 is clearly ahead on the aggregate, 64 to 31. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Claude Haiku 4.5 is also the more expensive model on tokens at $0.80 input / $4.00 output per 1M tokens, versus $0.05 input / $0.40 output per 1M tokens for GPT-5 nano. That is roughly 10.0x on output cost alone. GPT-5 nano 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. GPT-5 nano gives you the larger context window at 400K, compared with 200K for Claude Haiku 4.5.

Quick Verdict

Pick Claude Haiku 4.5 if you want the stronger benchmark profile. GPT-5 nano only becomes the better choice if mathematics is the priority or you want the cheaper token bill.

Knowledge

GPT-5 nano

Claude Haiku 4.5

57.8

GPT-5 nano

71.2

68
MMLU
-
67
GPQA
71.2
65
SuperGPQA
-
63
OpenBookQA
-
73
MMLU-Pro
-
11
HLE
-

Coding

Claude Haiku 4.5
60
HumanEval
-
48
SWE-bench Verified
-
36
LiveCodeBench
-

Mathematics

GPT-5 nano

Claude Haiku 4.5

68.8

GPT-5 nano

85.2

68
AIME 2023
-
70
AIME 2024
-
69
AIME 2025
85.2
64
HMMT Feb 2023
-
66
HMMT Feb 2024
-
65
HMMT Feb 2025
-
67
BRUMO 2025
-
81
MATH-500
-

Reasoning

Claude Haiku 4.5
65
SimpleQA
-
63
MuSR
-
81
BBH
-

Instruction Following

Claude Haiku 4.5
86
IFEval
-

Multilingual

Claude Haiku 4.5
82
MGSM
-

Frequently Asked Questions

Which is better, Claude Haiku 4.5 or GPT-5 nano?

Claude Haiku 4.5 is ahead overall, 64 to 31. The biggest single separator in this matchup is AIME 2025, where the scores are 69 and 85.2.

Which is better for knowledge tasks, Claude Haiku 4.5 or GPT-5 nano?

GPT-5 nano has the edge for knowledge tasks in this comparison, averaging 71.2 versus 57.8. Inside this category, GPQA is the benchmark that creates the most daylight between them.

Which is better for math, Claude Haiku 4.5 or GPT-5 nano?

GPT-5 nano has the edge for math in this comparison, averaging 85.2 versus 68.8. Inside this category, AIME 2025 is the benchmark that creates the most daylight between them.

Last updated: March 9, 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.