Beta
Compare · ModelsLive · 2 picked · head to head

Mistral Medium 3 vs Mixtral 8x7B Instruct

Side by side · benchmarks, pricing, and signals you can act on.

Winner summary

Mistral Medium 3 wins 2 of 2 shared benchmarks. Leads in knowledge · math.

Category leads
knowledge·Mistral Medium 3math·Mistral Medium 3
Hype vs Reality
Mistral Medium 3
#143 by perf·no signal
QUIET
Mixtral 8x7B Instruct
#52 by perf·no signal
QUIET
Best value
3.2x better value than Mistral Medium 3
Mistral Medium 3
33.3 pts/$
$1.20/M
Mixtral 8x7B Instruct
107.0 pts/$
$0.54/M
Vendor risk
Mistral AI logo
Mistral AI
$14.0B·Tier 1
Medium risk
Mistral AI logo
Mistral AI
$14.0B·Tier 1
Medium risk
Head to head
Mistral Medium 3Mixtral 8x7B Instruct
GPQA diamond
Mistral Medium 3 leads by +38.6
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Mistral Medium 3
46.0
Mixtral 8x7B Instruct
7.5
MATH level 5
Mistral Medium 3 leads by +71.7
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Mistral Medium 3
81.6
Mixtral 8x7B Instruct
9.9
Full benchmark table
BenchmarkMistral Medium 3Mixtral 8x7B Instruct
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
46.07.5
MATH level 5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
81.69.9
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
Mistral AI logoMistral Medium 3$0.40$2.00131K tokens (~66 books)$8.00
Mistral AI logoMixtral 8x7B Instruct$0.54$0.5433K tokens (~16 books)$5.40