Mistral AI · apache_2_0

Mistral Large 3 (675B Instruct 2512)

Mistral Large 3 (675B Instruct 2512) by Mistral AI appears in 1 source with Reasoning at 10.23. Best read for Low cost, Math, Multimodal.

CreatorMistral AI

Release date2025-12-04

Knowledge cutoffNot published

Context262K tokens

Input price$0.5/M tokens

Output price$1.5/M tokens

Modalitytext + vision

CountryFR

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank58ranking · source_rank

Reasoning10.23reasoning · index_reasoning

Math19.67math · index_math

Coding-0.22coding · index_code

GPQA43.9 %reasoning · gpqa_score

Code Arena868.55 %coding · coding_arena_score

MMMLU85.5 %reasoning · mmmlu_score

SimpleQA23.8 %knowledge · simpleqa_score

Context262,100 tokenscontext · context

Speed234.56 c/sperformance · throughput

Latency618.43 msperformance · latency

Input price0.5 $/Mpricing · input_price

Output price1.5 $/Mpricing · output_price

Parameters675,000,000,000 paramsmodel · params

Evidence

Citations and source overlap

LLM StatsPublic full LLM leaderboard advanced explorer snapshot, including ranking, benchmark indexes, pricing, speed, context, license, and model metadata.Retrieved 2026-06-01

FAQ

How should I read this profile?

Treat this as a source-backed model dossier, not an EvalKit-run verification. The public values are replicated from linked sources and kept source-scoped.

Is Mistral Large 3 (675B Instruct 2512) verified by EvalKit?

No. EvalKit currently shows 0 verified rows until real run evidence exists.

Why can metrics disagree?

Different sources test different tasks, dates, prompts, and aggregation methods. EvalKit keeps those differences visible instead of merging them into a fake universal score.