ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Llama-3.1-70B-Instruct vs Mixtral 8x7B vs WizardLM 2 8x22B

Llama-3.1-70B-Instruct comes out ahead, 39 to 32 and 25 on our weighted score, though WizardLM 2 8x22B is 32% cheaper per token.

Price in rating: Excluded · Include price

Retired Mixtral 8x7B is no longer offered by any provider we track. Its figures are the last published listing, kept so this comparison stays available.

  1. Our pick

    Meta

    Llama-3.1-70B-Instruct

    Released Jul 23, 2024

    39/100
    • ECI124.7
    • Price$0.72 / $0.72
    • Context128K
  2. Mistral AI

    Mixtral 8x7B

    Released Dec 11, 2023Retired

    25/100
    • ECI118.5
    • Price$0.70 / $0.70
    • Context32K
  3. Microsoft

    WizardLM 2 8x22B

    Released Apr 15, 2024

    32/100
    • ECI—
    • Price$0.493 / $0.493
    • Context66K
01 — Verdict

Llama-3.1-70B-Instruct is our pick

Llama-3.1-70B-Instruct is the better all-round choice, scoring 39/100 against WizardLM 2 8x22B (32) and Mixtral 8x7B (25). It leads on context window. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond), because WizardLM 2 8x22B has no Capabilities Index score yet.

  • CapabilityLlama-3.1-70B-InstructShared benchmarks: Llama-3.1-70B-Instruct 44.2% · WizardLM 2 8x22B 43.4% · Mixtral 8x7B 30.6%
  • Lowest priceWizardLM 2 8x22BWizardLM 2 8x22B $0.493 · Mixtral 8x7B $0.70 · Llama-3.1-70B-Instruct $0.72 per 1M tokens (3:1 blend)
  • Longest contextLlama-3.1-70B-InstructLlama-3.1-70B-Instruct 128,000 · WizardLM 2 8x22B 65,536 · Mixtral 8x7B 32,000 tokens
  • Widest inputsSame inputsLlama-3.1-70B-Instruct: Text · Mixtral 8x7B: Text · WizardLM 2 8x22B: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightLlama-3.1-70B-InstructMixtral 8x7BWizardLM 2 8x22B
CapabilityShared benchmarks67%443143
Inputs & features20%25250
Context window13%32022
Overall100%39/10025/10032/100
02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Llama-3.1-70B-Instruct vs Mixtral 8x7B vs WizardLM 2 8x22B specifications side by side
SpecificationLlama-3.1-70B-InstructMetaMixtral 8x7BMistral AIWizardLM 2 8x22BMicrosoft
Capability
Capabilities Index (ECI)124.7 (best)118.5—
ECI rank#146 of 158 (best)#153 of 158—
GPQA DiamondGraduate-level science questions44.2% (best)30.6%43.4%
OTIS Mock AIME 2024–2025Competition mathematics3.6%——
Price per million tokens
Input$0.72$0.70$0.493 (best)
Output$0.72$0.70$0.493 (best)
Cached input———
Blended (3:1)$0.72$0.70$0.493 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 7 providersOfficial Mistral APIMedian of 3 providers
Limits
Context window128,000 tokens (best)32,000 tokens65,536 tokens
Max output4,096 tokens32,000 tokens (best)8,000 tokens
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesNo
Structured outputNoNoNo
Availability
WeightsOpenOpenOpenApache-2.0
API model ID—open-mixtral-8x7b—
API providers7 (best)13
ReleasedJul 23, 2024Dec 11, 2023Apr 15, 2024
Knowledge cutoffDec 2023Jan 2024—
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Llama-3.1-70B-Instruct$8.64
  • Mixtral 8x7B$8.40
  • WizardLM 2 8x22B$5.92
04 — Questions

Which should you choose?

Which is better: Llama-3.1-70B-Instruct, Mixtral 8x7B or WizardLM 2 8x22B?

Llama-3.1-70B-Instruct is the better all-round choice, scoring 39/100 against WizardLM 2 8x22B (32) and Mixtral 8x7B (25). It leads on context window. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond), because WizardLM 2 8x22B has no Capabilities Index score yet.

Which is cheaper, Llama-3.1-70B-Instruct, Mixtral 8x7B or WizardLM 2 8x22B?

WizardLM 2 8x22B is cheaper at $0.493 input / $0.493 output per million tokens (median across 3 API providers). Mixtral 8x7B costs $0.70 input / $0.70 output per million tokens (official Mistral API price); Llama-3.1-70B-Instruct costs $0.72 input / $0.72 output per million tokens (median across 7 API providers). At a typical mix of three input tokens to one output token, that is $0.493 per million tokens for WizardLM 2 8x22B versus $0.70 for Mixtral 8x7B (1.4× as much) and $0.72 for Llama-3.1-70B-Instruct (1.5× as much).

Which scores higher on benchmarks?

Not every model here has a Capabilities Index score, so we compare the average of shared benchmarks (GPQA Diamond): Llama-3.1-70B-Instruct 44.2%, WizardLM 2 8x22B 43.4% and Mixtral 8x7B 30.6%. On individual benchmarks: GPQA Diamond — Llama-3.1-70B-Instruct 44.2%, WizardLM 2 8x22B 43.4%, Mixtral 8x7B 30.6%.

Which is better for coding?

There are no published SWE-bench Verified results for Llama-3.1-70B-Instruct, Mixtral 8x7B and WizardLM 2 8x22B yet, so there is no like-for-like coding score. On overall capability, Llama-3.1-70B-Instruct leads, which tends to carry over to coding, but test on your own codebase. Note that WizardLM 2 8x22B does not support tool calling, which most coding agents need.

Which has the bigger context window?

Llama-3.1-70B-Instruct has the largest context window at 128,000 tokens, against 65,536 for WizardLM 2 8x22B and 32,000 for Mixtral 8x7B. Maximum output per response: Llama-3.1-70B-Instruct up to 4,096, Mixtral 8x7B up to 32,000, WizardLM 2 8x22B up to 8,000 tokens.

Which can read images, PDFs, audio or video?

Llama-3.1-70B-Instruct accepts text; Mixtral 8x7B accepts text; WizardLM 2 8x22B accepts text. They handle the same number of input types.

Are any of these open source?

Yes, all three publish their weights (Apache-2.0), so you can self-host them.

Which is newer?

Llama-3.1-70B-Instruct is the newest, released Jul 23, 2024. WizardLM 2 8x22B came out Apr 15, 2024; Mixtral 8x7B came out Dec 11, 2023. Knowledge cutoff: Llama-3.1-70B-Instruct Dec 2023, Mixtral 8x7B Jan 2024.

How do you decide the winner?

This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 18, 2026.