WizardLM 2 8x22B vs Mixtral 8x7B Instruct v0.1 vs Llama-3.1-70B-Instruct
Llama-3.1-70B-Instruct comes out ahead, 42 to 38 and 31 on our weighted score, though Mixtral 8x7B Instruct v0.1 is 34% cheaper per token.
MicrosoftWizardLM 2 8x22B
38/100- ECI—
- Price$0.493 / $0.493
- Context66K
Mistral AIMixtral 8x7B Instruct v0.1
31/100- ECI118.4
- Price$0.444 / $0.579
- Context33K
- Our pick
MetaLlama-3.1-70B-Instruct
42/100- ECI125.9
- Price$0.72 / $0.72
- Context128K
Llama-3.1-70B-Instruct is our pick
Llama-3.1-70B-Instruct is the better all-round choice, scoring 42/100 against WizardLM 2 8x22B (38) and Mixtral 8x7B Instruct v0.1 (31). It leads on inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. 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 Instruct v0.1 30.6%
- Lowest priceMixtral 8x7B Instruct v0.1Mixtral 8x7B Instruct v0.1 $0.478 · WizardLM 2 8x22B $0.493 · 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 Instruct v0.1 32,768 tokens
- Widest inputsSame inputsWizardLM 2 8x22B: Text · Mixtral 8x7B Instruct v0.1: Text · Llama-3.1-70B-Instruct: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | WizardLM 2 8x22B | Mixtral 8x7B Instruct v0.1 | Llama-3.1-70B-Instruct |
|---|---|---|---|---|
| CapabilityShared benchmarks | 50% | 43 | 31 | 44 |
| Price | 25% | 62 | 62 | 54 |
| Inputs & features | 15% | 0 | 0 | 25 |
| Context window | 10% | 12 | 0 | 24 |
| Overall | 100% | 38/100 | 31/100 | 42/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | WizardLM 2 8x22BMicrosoft | Mixtral 8x7B Instruct v0.1Mistral AI | Llama-3.1-70B-InstructMeta |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 118.4 | 125.9 (best) |
| ECI rank | — | #160 of 165 | #149 of 165 (best) |
| GPQA DiamondGraduate-level science questions | 43.4% | 30.6% | 44.2% (best) |
| OTIS Mock AIME 2024–2025Competition mathematics | — | — | 3.6% |
| Price per million tokens | |||
| Input | $0.493 | $0.444 (best) | $0.72 |
| Output | $0.493 (best) | $0.579 | $0.72 |
| Cached input | — | — | — |
| Blended (3:1) | $0.493 | $0.478 (best) | $0.72 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 3 providers | Median of 2 providers | Median of 8 providers |
| Limits | |||
| Context window | 65,536 tokens | 32,768 tokens | 128,000 tokens (best) |
| Max output | 8,000 tokens | 32,768 tokens (best) | 4,096 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | No | No | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenApache-2.0 | OpenApache 2.0 | Open |
| API model ID | — | — | — |
| API providers | 3 | 2 | 8 (best) |
| Released | Apr 15, 2024 | Dec 11, 2023 | Jul 23, 2024 |
| Knowledge cutoff | — | — | Dec 2023 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- WizardLM 2 8x22B$5.92
- Mixtral 8x7B Instruct v0.1$5.60
- Llama-3.1-70B-Instruct$8.64
Which should you choose?
Which is better: WizardLM 2 8x22B, Mixtral 8x7B Instruct v0.1 or Llama-3.1-70B-Instruct?
Llama-3.1-70B-Instruct is the better all-round choice, scoring 42/100 against WizardLM 2 8x22B (38) and Mixtral 8x7B Instruct v0.1 (31). It leads on inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond), because WizardLM 2 8x22B has no Capabilities Index score yet.
Which is cheaper, WizardLM 2 8x22B, Mixtral 8x7B Instruct v0.1 or Llama-3.1-70B-Instruct?
Mixtral 8x7B Instruct v0.1 is cheaper at $0.444 input / $0.579 output per million tokens (median across 2 API providers). WizardLM 2 8x22B costs $0.493 input / $0.493 output per million tokens (median across 3 API providers); Llama-3.1-70B-Instruct costs $0.72 input / $0.72 output per million tokens (median across 8 API providers). At a typical mix of three input tokens to one output token, that is $0.478 per million tokens for Mixtral 8x7B Instruct v0.1 versus $0.493 for WizardLM 2 8x22B (1× 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 Instruct v0.1 30.6%. On individual benchmarks: GPQA Diamond — Llama-3.1-70B-Instruct 44.2%, WizardLM 2 8x22B 43.4%, Mixtral 8x7B Instruct v0.1 30.6%.
Which is better for coding?
There are no published SWE-bench Verified results for WizardLM 2 8x22B, Mixtral 8x7B Instruct v0.1 and Llama-3.1-70B-Instruct 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 and Mixtral 8x7B Instruct v0.1 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 32,768 for Mixtral 8x7B Instruct v0.1. Maximum output per response: WizardLM 2 8x22B up to 8,000, Mixtral 8x7B Instruct v0.1 up to 32,768, Llama-3.1-70B-Instruct up to 4,096 tokens.
Which can read images, PDFs, audio or video?
WizardLM 2 8x22B accepts text; Mixtral 8x7B Instruct v0.1 accepts text; Llama-3.1-70B-Instruct 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 and 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 Instruct v0.1 came out Dec 11, 2023. Knowledge cutoff: Llama-3.1-70B-Instruct Dec 2023.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, 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 2, 2026.
Related comparisons
- WizardLM 2 8x22B vs Mistral LargeMistral AI · ECI 122.0
- WizardLM 2 8x22B vs Claude Haiku 3Anthropic · ECI 118.8
- WizardLM 2 8x22B vs Gemma 2 27BGoogle · ECI 122.1
- Mixtral 8x7B Instruct v0.1 vs Claude Haiku 3Anthropic · ECI 118.8
- Mixtral 8x7B Instruct v0.1 vs Gemma 2 27BGoogle · ECI 122.1
- Mixtral 8x7B Instruct v0.1 vs GPT-4o miniOpenAI · ECI 126.5
