Llama-3.1-70B-Instruct vs QwQ 32B vs WizardLM 2 8x22B
QwQ 32B comes out ahead, 55 to 39 and 32 on our weighted score, though WizardLM 2 8x22B is 14% cheaper per token.
Price in rating: Excluded · Include price
Meta
Llama-3.1-70B-Instruct
39/100- ECI124.7
- Price$0.72 / $0.72
- Context128K
- Our pick
Alibaba (Qwen)
QwQ 32B
55/100- ECI136.5
- Price$0.53 / $0.70
- Context131K
Microsoft
WizardLM 2 8x22B
32/100- ECI—
- Price$0.493 / $0.493
- Context66K
QwQ 32B is our pick
QwQ 32B is the better all-round choice, scoring 55/100 against Llama-3.1-70B-Instruct (39) and WizardLM 2 8x22B (32). It leads on capability and inputs & features. 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.
- CapabilityQwQ 32BShared benchmarks: QwQ 32B 65.3% · Llama-3.1-70B-Instruct 44.2% · WizardLM 2 8x22B 43.4%
- Lowest priceWizardLM 2 8x22BWizardLM 2 8x22B $0.493 · QwQ 32B $0.573 · Llama-3.1-70B-Instruct $0.72 per 1M tokens (3:1 blend)
- Longest contextQwQ 32BQwQ 32B 131,072 · Llama-3.1-70B-Instruct 128,000 · WizardLM 2 8x22B 65,536 tokens
- Widest inputsSame inputsLlama-3.1-70B-Instruct: Text · QwQ 32B: Text · WizardLM 2 8x22B: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Llama-3.1-70B-Instruct | QwQ 32B | WizardLM 2 8x22B |
|---|---|---|---|---|
| CapabilityShared benchmarks | 67% | 44 | 65 | 43 |
| Inputs & features | 20% | 25 | 35 | 0 |
| Context window | 13% | 32 | 32 | 22 |
| Overall | 100% | 39/100 | 55/100 | 32/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 124.7 | 136.5 (best) | — |
| ECI rank | #146 of 158 | #122 of 158 (best) | — |
| GPQA DiamondGraduate-level science questions | 44.2% | 65.3% (best) | 43.4% |
| OTIS Mock AIME 2024–2025Competition mathematics | 3.6% | 59.2% (best) | — |
| Price per million tokens | |||
| Input | $0.72 | $0.53 | $0.493 (best) |
| Output | $0.72 | $0.70 | $0.493 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.72 | $0.573 | $0.493 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 7 providers | Median of 2 providers | Median of 3 providers |
| Limits | |||
| Context window | 128,000 tokens | 131,072 tokens (best) | 65,536 tokens |
| Max output | 4,096 tokens | 8,192 tokens (best) | 8,000 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 | Yes | No |
| Tool calling | Yes | Yes | No |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Open | OpenApache-2.0 |
| API model ID | — | — | — |
| API providers | 7 (best) | 2 | 3 |
| Released | Jul 23, 2024 | Mar 5, 2025 | Apr 15, 2024 |
| Knowledge cutoff | Dec 2023 | Apr 2024 | — |
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
QwQ 32B$6.70
WizardLM 2 8x22B$5.92
Which should you choose?
Which is better: Llama-3.1-70B-Instruct, QwQ 32B or WizardLM 2 8x22B?
QwQ 32B is the better all-round choice, scoring 55/100 against Llama-3.1-70B-Instruct (39) and WizardLM 2 8x22B (32). It leads on capability and inputs & features. 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, QwQ 32B or WizardLM 2 8x22B?
WizardLM 2 8x22B is cheaper at $0.493 input / $0.493 output per million tokens (median across 3 API providers). QwQ 32B costs $0.53 input / $0.70 output per million tokens (median across 2 API providers); 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 $0.573 for QwQ 32B (1.2× 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): QwQ 32B 65.3%, Llama-3.1-70B-Instruct 44.2% and WizardLM 2 8x22B 43.4%. On individual benchmarks: GPQA Diamond — QwQ 32B 65.3%, Llama-3.1-70B-Instruct 44.2%, WizardLM 2 8x22B 43.4%.
Which is better for coding?
There are no published SWE-bench Verified results for Llama-3.1-70B-Instruct, QwQ 32B and WizardLM 2 8x22B yet, so there is no like-for-like coding score. On overall capability, QwQ 32B 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?
QwQ 32B has the largest context window at 131,072 tokens, against 128,000 for Llama-3.1-70B-Instruct and 65,536 for WizardLM 2 8x22B. Maximum output per response: Llama-3.1-70B-Instruct up to 4,096, QwQ 32B up to 8,192, WizardLM 2 8x22B up to 8,000 tokens.
Which can read images, PDFs, audio or video?
Llama-3.1-70B-Instruct accepts text; QwQ 32B 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?
QwQ 32B is the newest, released Mar 5, 2025. Llama-3.1-70B-Instruct came out Jul 23, 2024; WizardLM 2 8x22B came out Apr 15, 2024. Knowledge cutoff: Llama-3.1-70B-Instruct Dec 2023, QwQ 32B Apr 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.