[–] ottomengis 23d ago ↗ [delayed] [–] tristanj 23d ago ↗ Benchmarks: https://www.vals.ai/models/mistralai_mistral-large-4It scores below GPT-6 Luna and Claude Sonnet 5. [–] dom96 23d ago ↗ Seems to be worse than MiMo v2.6 Pro in almost all aspects, in particular on cost, but also intelligence. Kinda disappointing.
[–] tristanj 23d ago ↗ Benchmarks: https://www.vals.ai/models/mistralai_mistral-large-4It scores below GPT-6 Luna and Claude Sonnet 5. [–] dom96 23d ago ↗ Seems to be worse than MiMo v2.6 Pro in almost all aspects, in particular on cost, but also intelligence. Kinda disappointing.
[–] dom96 23d ago ↗ Seems to be worse than MiMo v2.6 Pro in almost all aspects, in particular on cost, but also intelligence. Kinda disappointing.
4 comments
[ 4.4 ms ] story [ 13.6 ms ] threadIt scores below GPT-6 Luna and Claude Sonnet 5.