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 58. 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 mathematics, where it averages 96.7 against 23.1. The single biggest benchmark swing on the page is AIME 2024, 98 to 23.1.
GPT-5.3-Codex-Spark is also the more expensive model on tokens at $2.00 input / $8.00 output per 1M tokens, versus $0.40 input / $1.60 output per 1M tokens for GPT-4.1 mini. That is roughly 5.0x on output cost alone. GPT-5.3-Codex-Spark is the reasoning model in the pair, while GPT-4.1 mini 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-4.1 mini gives you the larger context window at 1M, compared with 256K for GPT-5.3-Codex-Spark.
Pick GPT-5.3-Codex-Spark if you want the stronger benchmark profile. GPT-4.1 mini only becomes the better choice if you want the cheaper token bill or you need the larger 1M context window.
GPT-5.3-Codex-Spark
85.6
GPT-4.1 mini
56.5
GPT-5.3-Codex-Spark
82.3
GPT-4.1 mini
28.8
GPT-5.3-Codex-Spark
88.3
GPT-4.1 mini
69.6
GPT-5.3-Codex-Spark
92.7
GPT-4.1 mini
80.9
GPT-5.3-Codex-Spark
78.3
GPT-4.1 mini
62.4
GPT-5.3-Codex-Spark
92
GPT-4.1 mini
88.5
GPT-5.3-Codex-Spark
90.8
GPT-4.1 mini
72
GPT-5.3-Codex-Spark
96.7
GPT-4.1 mini
23.1
GPT-5.3-Codex-Spark is ahead overall, 87 to 58. The biggest single separator in this matchup is AIME 2024, where the scores are 98 and 23.1.
GPT-5.3-Codex-Spark has the edge for knowledge tasks in this comparison, averaging 78.3 versus 62.4. Inside this category, GPQA is the benchmark that creates the most daylight between them.
GPT-5.3-Codex-Spark has the edge for coding in this comparison, averaging 82.3 versus 28.8. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
GPT-5.3-Codex-Spark has the edge for math in this comparison, averaging 96.7 versus 23.1. Inside this category, AIME 2024 is the benchmark that creates the most daylight between them.
GPT-5.3-Codex-Spark has the edge for reasoning in this comparison, averaging 92.7 versus 80.9. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.
GPT-5.3-Codex-Spark has the edge for agentic tasks in this comparison, averaging 85.6 versus 56.5. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
GPT-5.3-Codex-Spark has the edge for multimodal and grounded tasks in this comparison, averaging 88.3 versus 69.6. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
GPT-5.3-Codex-Spark has the edge for instruction following in this comparison, averaging 92 versus 88.5. Inside this category, IFEval is the benchmark that creates the most daylight between them.
GPT-5.3-Codex-Spark has the edge for multilingual tasks in this comparison, averaging 90.8 versus 72. Inside this category, MMLU-ProX is the benchmark that creates the most daylight between them.
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.