Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Kimi K2.5 (Reasoning) is clearly ahead on the aggregate, 76 to 27. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Kimi K2.5 (Reasoning)'s sharpest advantage is in coding, where it averages 64.1 against 6.2. The single biggest benchmark swing on the page is AIME 2023, 94 to 23.
Kimi K2.5 (Reasoning) is the reasoning model in the pair, while Ministral 3 3B 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.
Pick Kimi K2.5 (Reasoning) if you want the stronger benchmark profile. Ministral 3 3B only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.
Kimi K2.5 (Reasoning)
73.1
Ministral 3 3B
22.9
Kimi K2.5 (Reasoning)
64.1
Ministral 3 3B
6.2
Kimi K2.5 (Reasoning)
74.3
Ministral 3 3B
30.4
Kimi K2.5 (Reasoning)
84.9
Ministral 3 3B
30.1
Kimi K2.5 (Reasoning)
69.7
Ministral 3 3B
24.5
Kimi K2.5 (Reasoning)
91
Ministral 3 3B
67
Kimi K2.5 (Reasoning)
86.7
Ministral 3 3B
59.7
Kimi K2.5 (Reasoning)
92.6
Ministral 3 3B
36
Kimi K2.5 (Reasoning) is ahead overall, 76 to 27. The biggest single separator in this matchup is AIME 2023, where the scores are 94 and 23.
Kimi K2.5 (Reasoning) has the edge for knowledge tasks in this comparison, averaging 69.7 versus 24.5. Inside this category, MMLU is the benchmark that creates the most daylight between them.
Kimi K2.5 (Reasoning) has the edge for coding in this comparison, averaging 64.1 versus 6.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.
Kimi K2.5 (Reasoning) has the edge for math in this comparison, averaging 92.6 versus 36. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
Kimi K2.5 (Reasoning) has the edge for reasoning in this comparison, averaging 84.9 versus 30.1. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.
Kimi K2.5 (Reasoning) has the edge for agentic tasks in this comparison, averaging 73.1 versus 22.9. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Kimi K2.5 (Reasoning) has the edge for multimodal and grounded tasks in this comparison, averaging 74.3 versus 30.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
Kimi K2.5 (Reasoning) has the edge for instruction following in this comparison, averaging 91 versus 67. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Kimi K2.5 (Reasoning) has the edge for multilingual tasks in this comparison, averaging 86.7 versus 59.7. 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.