Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Mistral Large 3 is clearly ahead on the aggregate, 68 to 39. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Mistral Large 3's sharpest advantage is in multilingual, where it averages 82 against 80.6. The single biggest benchmark swing on the page is GPQA, 75 to 56.1. Phi-4 does hit back in coding, so the answer changes if that is the part of the workload you care about most.
Mistral Large 3 is also the more expensive model on tokens at $2.00 input / $6.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Phi-4. That is roughly Infinityx on output cost alone. Mistral Large 3 gives you the larger context window at 128K, compared with 16K for Phi-4.
Pick Mistral Large 3 if you want the stronger benchmark profile. Phi-4 only becomes the better choice if coding is the priority or you want the cheaper token bill.
Mistral Large 3
63.5
Phi-4
70.5
Mistral Large 3
50.7
Phi-4
82.6
Mistral Large 3
82
Phi-4
80.6
Mistral Large 3 is ahead overall, 68 to 39. The biggest single separator in this matchup is GPQA, where the scores are 75 and 56.1.
Phi-4 has the edge for knowledge tasks in this comparison, averaging 70.5 versus 63.5. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Phi-4 has the edge for coding in this comparison, averaging 82.6 versus 50.7. Inside this category, HumanEval is the benchmark that creates the most daylight between them.
Mistral Large 3 has the edge for multilingual tasks in this comparison, averaging 82 versus 80.6. 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.