NEWMEN
← back to all models

Mistral: Mistral Medium 3

mistralai/mistral-medium-3

Mistralopen-weight131K context1 providerIntelligence 68.0

Cheapest provider

$0.40 / 1M

Mistral

Fastest provider (p95)

49 tok/s

Mistral

Intelligence (composite)

68.0

MMLU-Pro · HumanEval · math · GPQA

Per-provider performance

Latency / throughput / uptime measured across providers over the last 30 minutes of live traffic. Atlas’s router weighs these per call (with the eval-gate signal) when picking a variant for Standard and Batch tiers.

ProviderQuantInput $/1MOutput $/1MLatency p50 / p95Throughput p50 / p95Uptime 30mSuccess
Mistralundisclosed$0.4000$2.0000420ms / 1829ms38 / 48.5 tok/s100.0%

“—” means live telemetry hasn’t accumulated enough recent traffic for that endpoint. “undisclosed” means the provider serves the model but doesn’t expose the quantization label (typically running fp8 / int8 internally).

Intelligence breakdown

Composite score is a weighted average of public benchmarks (30% MMLU-Pro, 25% code pass@1, 25% math, 20% GPQA). Numbers come from model cards and the Artificial Analysis intelligence harness; missing components are renormalised over what’s present.

MMLU-Pro

67.6

broad reasoning

Code

83.4

pass@1 (HumanEval / LiveCodeBench)

MATH

71.4

math accuracy

GPQA Diamond

45.2

hard reasoning

Source: Mistral Medium 3 announcement (2025)

How Atlas routes Mistral: Mistral Medium 3

  • Realtime tier — direct passthrough at the upstream’s native precision. Best for hard latency / quality guarantees.
  • Standard tier — Atlas picks the cheapest provider variant whose quantization has stayed green on your operation’s eval gates. For Mistral: Mistral Medium 3 that’s currently Mistral at $0.40/1M.
  • Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.