Llama-3.1-70B-Instruct vs Gemma 3 27B IT vs WizardLM 2 8x22B
Gemma 3 27B IT comes out ahead, 56 to 43 and 39 on our weighted score, and it is the cheaper option too.
Price in rating: Included · Exclude price
Meta
Llama-3.1-70B-Instruct
43/100- ECI124.7
- Price$0.72 / $0.72
- Context128K
- Our pick
Google
Gemma 3 27B IT
56/100- ECI127.5
- Price$0.10 / $0.299
- Context131K
Microsoft
WizardLM 2 8x22B
39/100- ECI—
- Price$0.493 / $0.493
- Context66K
Gemma 3 27B IT is our pick
Gemma 3 27B IT is the better all-round choice, scoring 56/100 against Llama-3.1-70B-Instruct (43) and WizardLM 2 8x22B (39). It leads on capability, price and inputs & features. 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.
- CapabilityGemma 3 27B ITShared benchmarks: Gemma 3 27B IT 47.7% · Llama-3.1-70B-Instruct 44.2% · WizardLM 2 8x22B 43.4%
- Lowest priceGemma 3 27B ITGemma 3 27B IT $0.15 · WizardLM 2 8x22B $0.493 · Llama-3.1-70B-Instruct $0.72 per 1M tokens (3:1 blend)
- Longest contextGemma 3 27B ITGemma 3 27B IT 131,072 · Llama-3.1-70B-Instruct 128,000 · WizardLM 2 8x22B 65,536 tokens
- Widest inputsGemma 3 27B ITLlama-3.1-70B-Instruct: Text · Gemma 3 27B IT: Text, Images · 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 | Gemma 3 27B IT | WizardLM 2 8x22B |
|---|---|---|---|---|
| CapabilityShared benchmarks | 50% | 44 | 48 | 43 |
| Price | 25% | 54 | 85 | 62 |
| Inputs & features | 15% | 25 | 50 | 0 |
| Context window | 10% | 32 | 32 | 22 |
| Overall | 100% | 43/100 | 56/100 | 39/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 124.7 | 127.5 (best) | — |
| ECI rank | #146 of 158 | #141 of 158 (best) | — |
| GPQA DiamondGraduate-level science questions | 44.2% | 47.7% (best) | 43.4% |
| OTIS Mock AIME 2024–2025Competition mathematics | 3.6% | 22.5% (best) | — |
| Price per million tokens | |||
| Input | $0.72 | $0.10 (best) | $0.493 |
| Output | $0.72 | $0.299 (best) | $0.493 |
| Cached input | — | — | — |
| Blended (3:1) | $0.72 | $0.15 (best) | $0.493 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 7 providers | Median of 17 providers | Median of 3 providers |
| Limits | |||
| Context window | 128,000 tokens | 131,072 tokens (best) | 65,536 tokens |
| Max output | 4,096 tokens | 131,072 tokens (best) | 8,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | Yes | Yes | No |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Open | OpenApache-2.0 |
| API model ID | — | — | — |
| API providers | 7 | 18 (best) | 3 |
| Released | Jul 23, 2024 | Mar 12, 2025 | Apr 15, 2024 |
| Knowledge cutoff | Dec 2023 | Aug 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
Gemma 3 27B IT$1.60
WizardLM 2 8x22B$5.92
Which should you choose?
Which is better: Llama-3.1-70B-Instruct, Gemma 3 27B IT or WizardLM 2 8x22B?
Gemma 3 27B IT is the better all-round choice, scoring 56/100 against Llama-3.1-70B-Instruct (43) and WizardLM 2 8x22B (39). It leads on capability, price and inputs & features. 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, Llama-3.1-70B-Instruct, Gemma 3 27B IT or WizardLM 2 8x22B?
Gemma 3 27B IT is cheaper at $0.10 input / $0.299 output per million tokens (median across 17 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 7 API providers). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for Gemma 3 27B IT versus $0.493 for WizardLM 2 8x22B (3.3× as much) and $0.72 for Llama-3.1-70B-Instruct (4.8× 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): Gemma 3 27B IT 47.7%, Llama-3.1-70B-Instruct 44.2% and WizardLM 2 8x22B 43.4%. On individual benchmarks: GPQA Diamond — Gemma 3 27B IT 47.7%, 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, Gemma 3 27B IT and WizardLM 2 8x22B yet, so there is no like-for-like coding score. On overall capability, Gemma 3 27B IT 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?
Gemma 3 27B IT 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, Gemma 3 27B IT up to 131,072, WizardLM 2 8x22B up to 8,000 tokens.
Which can read images, PDFs, audio or video?
Llama-3.1-70B-Instruct accepts text; Gemma 3 27B IT accepts text and images; WizardLM 2 8x22B accepts text. Gemma 3 27B IT handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (Apache-2.0), so you can self-host them.
Which is newer?
Gemma 3 27B IT is the newest, released Mar 12, 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, Gemma 3 27B IT Aug 2024.
How do you decide the winner?
This rating uses 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 18, 2026.