Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Kimi K2.5 is clearly ahead on the aggregate, 60 to 31. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Kimi K2.5's sharpest advantage is in mathematics, where it averages 78.7 against 40.9. The single biggest benchmark swing on the page is HumanEval, 69 to 16.
Kimi K2.5 is also the more expensive model on tokens at $0.50 input / $2.80 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Ministral 3 3B (Reasoning). That is roughly Infinityx on output cost alone. Ministral 3 3B (Reasoning) is the reasoning model in the pair, while Kimi K2.5 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.
Pick Kimi K2.5 if you want the stronger benchmark profile. Ministral 3 3B (Reasoning) only becomes the better choice if you want the cheaper token bill or you want the stronger reasoning-first profile.
Kimi K2.5
52.3
Ministral 3 3B (Reasoning)
34
Kimi K2.5
38.9
Ministral 3 3B (Reasoning)
7.2
Kimi K2.5
64.6
Ministral 3 3B (Reasoning)
30.4
Kimi K2.5
71.7
Ministral 3 3B (Reasoning)
35.3
Kimi K2.5
57.2
Ministral 3 3B (Reasoning)
25.2
Kimi K2.5
85
Ministral 3 3B (Reasoning)
68
Kimi K2.5
79.8
Ministral 3 3B (Reasoning)
59.7
Kimi K2.5
78.7
Ministral 3 3B (Reasoning)
40.9
Kimi K2.5 is ahead overall, 60 to 31. The biggest single separator in this matchup is HumanEval, where the scores are 69 and 16.
Kimi K2.5 has the edge for knowledge tasks in this comparison, averaging 57.2 versus 25.2. Inside this category, MMLU is the benchmark that creates the most daylight between them.
Kimi K2.5 has the edge for coding in this comparison, averaging 38.9 versus 7.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.
Kimi K2.5 has the edge for math in this comparison, averaging 78.7 versus 40.9. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
Kimi K2.5 has the edge for reasoning in this comparison, averaging 71.7 versus 35.3. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.
Kimi K2.5 has the edge for agentic tasks in this comparison, averaging 52.3 versus 34. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.
Kimi K2.5 has the edge for multimodal and grounded tasks in this comparison, averaging 64.6 versus 30.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
Kimi K2.5 has the edge for instruction following in this comparison, averaging 85 versus 68. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Kimi K2.5 has the edge for multilingual tasks in this comparison, averaging 79.8 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.