Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Ministral 3 14B has the cleaner overall profile here, landing at 55 versus 52. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Ministral 3 14B's sharpest advantage is in reasoning, where it averages 63.6 against 49.4. The single biggest benchmark swing on the page is SWE-bench Pro, 34 to 65. GPT-4o mini does hit back in coding, so the answer changes if that is the part of the workload you care about most.
GPT-4o mini is also the more expensive model on tokens at $0.15 input / $0.60 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Ministral 3 14B. That is roughly Infinityx on output cost alone.
Pick Ministral 3 14B if you want the stronger benchmark profile. GPT-4o mini only becomes the better choice if coding is the priority.
Ministral 3 14B
48.4
GPT-4o mini
50.9
Ministral 3 14B
33
GPT-4o mini
65
Ministral 3 14B
70.5
GPT-4o mini
60.2
Ministral 3 14B
63.6
GPT-4o mini
49.4
Ministral 3 14B
50.1
GPT-4o mini
62
Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.
Ministral 3 14B
76.8
GPT-4o mini
74.7
Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.
Ministral 3 14B is ahead overall, 55 to 52. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 34 and 65.
GPT-4o mini has the edge for knowledge tasks in this comparison, averaging 62 versus 50.1. Inside this category, MMLU is the benchmark that creates the most daylight between them.
GPT-4o mini has the edge for coding in this comparison, averaging 65 versus 33. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
Ministral 3 14B has the edge for reasoning in this comparison, averaging 63.6 versus 49.4. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.
GPT-4o mini has the edge for agentic tasks in this comparison, averaging 50.9 versus 48.4. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Ministral 3 14B has the edge for multimodal and grounded tasks in this comparison, averaging 70.5 versus 60.2. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.
Ministral 3 14B has the edge for multilingual tasks in this comparison, averaging 76.8 versus 74.7. 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.