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 59. 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 38.7. The single biggest benchmark swing on the page is LiveCodeBench, 80 to 35.
GPT-5.3-Codex-Spark is also the more expensive model on tokens at $2.00 input / $8.00 output per 1M tokens, versus $0.30 input / $1.20 output per 1M tokens for MiniMax M2.5. That is roughly 6.7x on output cost alone. GPT-5.3-Codex-Spark is the reasoning model in the pair, while MiniMax M2.5 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-5.3-Codex-Spark gives you the larger context window at 256K, compared with 128K for MiniMax M2.5.
Pick GPT-5.3-Codex-Spark if you want the stronger benchmark profile. MiniMax M2.5 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.
GPT-5.3-Codex-Spark
85.6
MiniMax M2.5
53.4
GPT-5.3-Codex-Spark
82.3
MiniMax M2.5
38.7
GPT-5.3-Codex-Spark
88.3
MiniMax M2.5
62
GPT-5.3-Codex-Spark
92.7
MiniMax M2.5
69.6
GPT-5.3-Codex-Spark
78.3
MiniMax M2.5
55.3
GPT-5.3-Codex-Spark
92
MiniMax M2.5
85
GPT-5.3-Codex-Spark
90.8
MiniMax M2.5
82.1
GPT-5.3-Codex-Spark
96.7
MiniMax M2.5
76.1
GPT-5.3-Codex-Spark is ahead overall, 87 to 59. The biggest single separator in this matchup is LiveCodeBench, where the scores are 80 and 35.
GPT-5.3-Codex-Spark has the edge for knowledge tasks in this comparison, averaging 78.3 versus 55.3. Inside this category, HLE 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 38.7. Inside this category, LiveCodeBench 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 76.1. Inside this category, AIME 2023 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 69.6. 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 53.4. 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 62. 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 85. 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 82.1. Inside this category, MGSM 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.