GPT-5.3-Codex-Spark vs LFM2-24B-A2B

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

GPT-5.3-Codex-Spark is clearly ahead on the aggregate, 87 to 38. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-5.3-Codex-Spark's sharpest advantage is in coding, where it averages 82.3 against 18. The single biggest benchmark swing on the page is SWE-bench Pro, 85 to 19.

GPT-5.3-Codex-Spark is also the more expensive model on tokens at $2.00 input / $8.00 output per 1M tokens, versus $0.03 input / $0.12 output per 1M tokens for LFM2-24B-A2B. That is roughly 66.7x on output cost alone. GPT-5.3-Codex-Spark is the reasoning model in the pair, while LFM2-24B-A2B 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-5.3-Codex-Spark gives you the larger context window at 256K, compared with 32K for LFM2-24B-A2B.

Quick Verdict

Pick GPT-5.3-Codex-Spark if you want the stronger benchmark profile. LFM2-24B-A2B only becomes the better choice if you want the cheaper token bill or you would rather avoid the extra latency and token burn of a reasoning model.

Agentic

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

85.6

LFM2-24B-A2B

33.4

90
Terminal-Bench 2.0
30
82
BrowseComp
38
83
OSWorld-Verified
34

Coding

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

82.3

LFM2-24B-A2B

18

91
HumanEval
42
80
SWE-bench Verified
18
80
LiveCodeBench
17
85
SWE-bench Pro
19

Multimodal & Grounded

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

88.3

LFM2-24B-A2B

41.7

86
MMMU-Pro
39
91
OfficeQA Pro
45

Reasoning

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

92.7

LFM2-24B-A2B

46.6

94
SimpleQA
44
92
MuSR
42
97
BBH
63
91
LongBench v2
48
92
MRCRv2
45

Knowledge

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

78.3

LFM2-24B-A2B

35.6

97
MMLU
46
95
GPQA
45
93
SuperGPQA
43
91
OpenBookQA
41
88
MMLU-Pro
51
42
HLE
4
88
FrontierScience
43

Instruction Following

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

92

LFM2-24B-A2B

68

92
IFEval
68

Multilingual

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

90.8

LFM2-24B-A2B

61.4

94
MGSM
64
89
MMLU-ProX
60

Mathematics

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

96.7

LFM2-24B-A2B

50.4

98
AIME 2023
46
98
AIME 2024
48
97
AIME 2025
47
94
HMMT Feb 2023
42
96
HMMT Feb 2024
44
95
HMMT Feb 2025
43
95
BRUMO 2025
45
98
MATH-500
57

Frequently Asked Questions

Which is better, GPT-5.3-Codex-Spark or LFM2-24B-A2B?

GPT-5.3-Codex-Spark is ahead overall, 87 to 38. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 85 and 19.

Which is better for knowledge tasks, GPT-5.3-Codex-Spark or LFM2-24B-A2B?

GPT-5.3-Codex-Spark has the edge for knowledge tasks in this comparison, averaging 78.3 versus 35.6. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, GPT-5.3-Codex-Spark or LFM2-24B-A2B?

GPT-5.3-Codex-Spark has the edge for coding in this comparison, averaging 82.3 versus 18. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for math, GPT-5.3-Codex-Spark or LFM2-24B-A2B?

GPT-5.3-Codex-Spark has the edge for math in this comparison, averaging 96.7 versus 50.4. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, GPT-5.3-Codex-Spark or LFM2-24B-A2B?

GPT-5.3-Codex-Spark has the edge for reasoning in this comparison, averaging 92.7 versus 46.6. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GPT-5.3-Codex-Spark or LFM2-24B-A2B?

GPT-5.3-Codex-Spark has the edge for agentic tasks in this comparison, averaging 85.6 versus 33.4. 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-5.3-Codex-Spark or LFM2-24B-A2B?

GPT-5.3-Codex-Spark has the edge for multimodal and grounded tasks in this comparison, averaging 88.3 versus 41.7. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, GPT-5.3-Codex-Spark or LFM2-24B-A2B?

GPT-5.3-Codex-Spark has the edge for instruction following in this comparison, averaging 92 versus 68. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, GPT-5.3-Codex-Spark or LFM2-24B-A2B?

GPT-5.3-Codex-Spark has the edge for multilingual tasks in this comparison, averaging 90.8 versus 61.4. 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.