ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Llama 3.3 70B InstructvsMistral Small 4

Mistral Small 4 leads 2 of 2 shared benchmarks. Mistral Small 4 has the larger context window (256K tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
0 – 2
Mistral Small 4 leads
Cheaper per token
list price, input + output
Larger context
Mistral Small 4
256K tokens
Provider uptime (30d)
— · 100%
Meta · Mistral AI
Llama 3.3 70B Instruct
Meta · released 2024-12-06
text
Context
131K
Max out
Input /1M
Output /1M
Cached /1M
Scores
5 · 4 core
Mistral Small 4
Mistral AI · released 2026-03-16
textvision
Context
256K
Max out
Input /1M
$0.15
Output /1M
$0.6
Cached /1M
$0.015
Scores
3 · 2 core
Quality

Benchmark matrix

BenchmarkLlama 3.3 70B InstructMistral Small 4ΔEdge
Reported by both · 2
GPQA Diamond50.5% 71.2% -20.7 ptMistral Small 4
MMLU-Pro68.9% 78% -9.1 ptMistral Small 4
Only Llama 3.3 70B Instruct reports · 2
LMArena Elo1274 not reported
OTIS Mock AIME 2024-2025 (Epoch AI run)5.1% epochnot reported
Only Mistral Small 4 reports · 1
Artificial Analysis Long Context Reasoningnot reported0.72
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Llama 3.3 70B Instruct minus Mistral Small 4 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecLlama 3.3 70B InstructMistral Small 4Edge
Context window131K tokens256K tokensMistral Small 4
Max output
Input price / 1M$0.15
Output price / 1M$0.6
Cached input / 1M$0.015
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$0.75
Modalitiestexttext · visionMistral Small 4
Released2024-12-062026-03-16
Cited benchmark scores53
Reliability

Provider status

All providers
More matchups

Llama 3.3 70B Instruct vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Llama 3.3 70B Instruct and Mistral Small 4 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.