Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Claude 3.5 Sonnet is clearly ahead on the aggregate, 60 to 36. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Claude 3.5 Sonnet's sharpest advantage is in multimodal & grounded, where it averages 74.8 against 33.4. The single biggest benchmark swing on the page is MMMU-Pro, 77 to 28.
Ministral 3 8B (Reasoning) is the reasoning model in the pair, while Claude 3.5 Sonnet 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. Claude 3.5 Sonnet gives you the larger context window at 200K, compared with 128K for Ministral 3 8B (Reasoning).
Pick Claude 3.5 Sonnet if you want the stronger benchmark profile. Ministral 3 8B (Reasoning) only becomes the better choice if you want the stronger reasoning-first profile.
Claude 3.5 Sonnet
55
Ministral 3 8B (Reasoning)
38.5
Claude 3.5 Sonnet
37.8
Ministral 3 8B (Reasoning)
15.2
Claude 3.5 Sonnet
74.8
Ministral 3 8B (Reasoning)
33.4
Claude 3.5 Sonnet
67.7
Ministral 3 8B (Reasoning)
42.1
Claude 3.5 Sonnet
50.8
Ministral 3 8B (Reasoning)
30
Claude 3.5 Sonnet
83
Ministral 3 8B (Reasoning)
70
Claude 3.5 Sonnet
80.5
Ministral 3 8B (Reasoning)
61.7
Claude 3.5 Sonnet
71.2
Ministral 3 8B (Reasoning)
47.8
Claude 3.5 Sonnet is ahead overall, 60 to 36. The biggest single separator in this matchup is MMMU-Pro, where the scores are 77 and 28.
Claude 3.5 Sonnet has the edge for knowledge tasks in this comparison, averaging 50.8 versus 30. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Claude 3.5 Sonnet has the edge for coding in this comparison, averaging 37.8 versus 15.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.
Claude 3.5 Sonnet has the edge for math in this comparison, averaging 71.2 versus 47.8. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
Claude 3.5 Sonnet has the edge for reasoning in this comparison, averaging 67.7 versus 42.1. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.
Claude 3.5 Sonnet has the edge for agentic tasks in this comparison, averaging 55 versus 38.5. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.
Claude 3.5 Sonnet has the edge for multimodal and grounded tasks in this comparison, averaging 74.8 versus 33.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
Claude 3.5 Sonnet has the edge for instruction following in this comparison, averaging 83 versus 70. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Claude 3.5 Sonnet has the edge for multilingual tasks in this comparison, averaging 80.5 versus 61.7. 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.