Llama vs Mistral

A live, data-driven comparison of Llama and Mistral — top models from each brand, 7+ benchmarks, API pricing across every provider, and how each brand's models have evolved over time.

Get our weekly newsletter on pricing changes, new releases, and tools.

Llama vs Mistral: the short answer

Mistral has the cheapest API option (Mistral Nemo at $0.02/M input). Full benchmark, pricing, and capability breakdown below.

Cheapest API
Mistral Nemo
$0.02 / M in
Best for coding
—
— coding
Biggest context
Llama 4 Scout 17B 16E Instruct FP8 LoRA
10486K tokens
Newest model
Muse Spark Open
2026-10-15

Benchmarks: Llama vs Mistral at their best

Each bar is the best score any Llama or Mistral model achieves on that benchmark. Only benchmarks where both brands have a score are shown.

LlamaMistral

🧠 Intelligence & Knowledge

Intelligence IndexLlama 3.3 70B Instruct vs Mistral Nemo
44.9
25.0
MMLU-ProLlama 3.3 70B Instruct vs Mistral Nemo
48.1
26.4
GPQAMuse Spark 1.3 vs Mistral Nemo
93.5
8.7
Big-Bench HardLlama 3.3 70B Instruct vs Mistral Nemo
56.6
36.1

💻 Coding

AiderLlama 3.1 405B Instruct vs Mistral Large 2411
66.2
65.4

🔢 Math

MATH (Hard)Llama 3.3 70B Instruct vs Mistral Nemo
48.3
7.4

📝 Instruction Following

IFEvalLlama 3.3 70B Instruct vs Mistral Nemo
90.0
56.0

Model releases over time

Every Llama and Mistral model with a known release date, on one timeline — the release cadence of each brand at a glance.

Model Release Timeline

24 releases
Mar 2025
$0.10 / $0.30
Apr 2025
$0.10 / $0.30
Apr 2025
$0.20 / $0.60
May 2025
$0.44 / $2.20
Jun 2025
$0.07 / $0.20
Jul 2025
$0.07 / $0.28
Jul 2025
$0.40 / $2.00
Aug 2025
$0.30 / $0.90
Aug 2025
$0.44 / $2.20
Oct 2025
$0.10 / $0.30
Dec 2025
$0.50 / $1.50
Dec 2025
$0.10 / $0.10
Dec 2025
$0.15 / $0.15
Dec 2025
$0.20 / $0.20
Dec 2025
$0.40 / $0.90
Dec 2025
$0.10 / $0.30
Mar 2026
$0.15 / $0.60
Apr 2026
$1.50 / $7.50
Aug 2026
$0.30 / $0.90
Aug 2026
$0.10 / $0.20
Sep 2026
$1.25 / $4.25
Sep 2026
$0.10 / $0.20
Oct 2026
$0.70 / $2.10
Oct 2026
$1.25 / $4.25
Spacing represents time between releases
Mar 2025→Oct 2026

Pricing & Models

Llama
ModelInput /MOutput /MContextCoding
Muse Spark Open$1.25$4.251049K—
Muse Spark 1.3 Contributor$0.10$0.201049K—
Muse Spark 1.3$1.25$4.251049K—
Muse Spark 1.2$0.10$0.201049K—
Muse Glimmer 30B$0.30$0.90131K—
Llama 4 Maverick$0.20$0.601049K—
Llama 4 Scout$0.10$0.30328K—
Llama 3.3 70B Instruct$0.10$0.32131K—
Mistral
ModelInput /MOutput /MContextCoding
Mistral Large 4$0.70$2.101049K—
Mistral Medium 3.5$1.50$7.50262K—
Mistral Small 2603$0.15$0.60262K—
Mistral Small Creative$0.10$0.3033K—
Devstral 2 2512$0.40$0.90262K—
Ministral 3 14B 2512$0.20$0.20262K—
Ministral 3 8B 2512$0.15$0.15262K—
Ministral 3 3B 2512$0.10$0.10131K—

Prices are per 1M tokens, lowest available across API providers. Showing the 8 most recent models per brand.

Frequently Asked Questions

Neither wins outright — it depends on the task. Use the benchmark and pricing breakdown above to pick the right model for your workload.
Llama's cheapest model starts at $0.02/M input tokens and Mistral's starts at $0.02/M. Mistral is the cheaper option at the low end. See per-provider API pricing above for exact costs.
The largest context window across these brands is Llama 4 Scout 17B 16E Instruct FP8 LoRA at 10486K tokens. Per-model context windows are in the pricing tables above.
If you're building an app or calling models programmatically, the API (priced per token above) is usually cheaper for bursty or low-volume use. A monthly chat subscription can be better for heavy daily interactive use. Compare your expected token volume against the per-token prices above.
Yes — many teams route different tasks to different models. Several API providers (e.g. OpenRouter) expose both Llama and Mistral models behind one API, and the per-provider pricing above shows where each is cheapest.