Gemma 2 2B IT vs Gemma 3 12B IT vs Hermes 3 405B Instruct
Gemma 3 12B IT comes out ahead, 40 to 10 and 0 on our weighted score, and it is the cheaper option too.
GoogleGemma 2 2B IT
0/100- ECI—
- Price—
- Context8K
- Our pickGoogle
Gemma 3 12B IT
40/100- ECI123.5
- Price$0.05 / $0.15
- Context131K
Nous ResearchHermes 3 405B Instruct
10/100- ECI—
- Price$1.00 / $1.00
- Context131K
Gemma 3 12B IT is our pick
Gemma 3 12B IT is the better all-round choice, scoring 40/100 against Hermes 3 405B Instruct (10) and Gemma 2 2B IT (0). It leads on inputs & features. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceGemma 3 12B ITGemma 3 12B IT $0.075 · Hermes 3 405B Instruct $1.00 per 1M tokens (3:1 blend) · Gemma 2 2B IT unpriced
- Longest contextGemma 3 12B IT and Hermes 3 405B InstructGemma 3 12B IT 131,072 · Hermes 3 405B Instruct 131,072 · Gemma 2 2B IT 8,192 tokens
- Widest inputsGemma 3 12B ITGemma 2 2B IT: Text · Gemma 3 12B IT: Text, Images · Hermes 3 405B Instruct: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Gemma 2 2B IT | Gemma 3 12B IT | Hermes 3 405B Instruct |
|---|---|---|---|---|
| Inputs & features | 60% | 0 | 50 | 0 |
| Context window | 40% | 0 | 25 | 25 |
| Overall | 100% | 0/100 | 40/100 | 10/100 |
Left out because at least one model lacks the data: capability and price. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Gemma 2 2B ITGoogle | Gemma 3 12B ITGoogle | Hermes 3 405B InstructNous Research |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 123.5 | — |
| ECI rank | — | #151 of 165 | — |
| GPQA DiamondGraduate-level science questions | — | 39.5% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 16.7% | — |
| Price per million tokens | |||
| Input | — | $0.05 (best) | $1.00 |
| Output | — | $0.15 (best) | $1.00 |
| Cached input | — | — | — |
| Blended (3:1) | — | $0.075 (best) | $1.00 |
| Long-context rate | — | Same rate | Same rate |
| Price source | — | Median of 12 providers | Median of 5 providers |
| Limits | |||
| Context window | 8,192 tokens | 131,072 tokens (best) | 131,072 tokens (best) |
| Max output | 8,192 tokens | 131,072 tokens (best) | 16,384 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 | No | Yes | No |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenGemma Terms of Use | Open | Open |
| API model ID | — | — | — |
| API providers | — | 13 (best) | 5 |
| Released | Jul 31, 2024 | Mar 12, 2025 | Aug 16, 2024 |
| Knowledge cutoff | — | Aug 2024 | Dec 31, 2023 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Gemma 2 2B IT—
- Gemma 3 12B IT$0.80
- Hermes 3 405B Instruct$12.00
Which should you choose?
Which is better: Gemma 2 2B IT, Gemma 3 12B IT or Hermes 3 405B Instruct?
Gemma 3 12B IT is the better all-round choice, scoring 40/100 against Hermes 3 405B Instruct (10) and Gemma 2 2B IT (0). It leads on inputs & features. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Gemma 2 2B IT, Gemma 3 12B IT or Hermes 3 405B Instruct?
Gemma 3 12B IT is cheaper at $0.05 input / $0.15 output per million tokens (median across 12 API providers). Hermes 3 405B Instruct costs $1.00 input / $1.00 output per million tokens (median across 5 API providers). At a typical mix of three input tokens to one output token, that is $0.075 per million tokens for Gemma 3 12B IT versus $1.00 for Hermes 3 405B Instruct (13× as much). Gemma 2 2B IT has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Gemma 2 2B IT has not been scored yet, Gemma 3 12B IT has an ECI of 123.5 and Hermes 3 405B Instruct has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Gemma 2 2B IT, Gemma 3 12B IT and Hermes 3 405B Instruct yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Gemma 2 2B IT and Hermes 3 405B Instruct does not support tool calling, which most coding agents need.
Which has the bigger context window?
Gemma 3 12B IT and Hermes 3 405B Instruct have the largest context windows (131,072 and 131,072 tokens), against 8,192 for Gemma 2 2B IT. Maximum output per response: Gemma 2 2B IT up to 8,192, Gemma 3 12B IT up to 131,072, Hermes 3 405B Instruct up to 16,384 tokens.
Which can read images, PDFs, audio or video?
Gemma 2 2B IT accepts text; Gemma 3 12B IT accepts text and images; Hermes 3 405B Instruct accepts text. Gemma 3 12B IT handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (Gemma Terms of Use), so you can self-host them.
Which is newer?
Gemma 3 12B IT is the newest, released Mar 12, 2025. Hermes 3 405B Instruct came out Aug 16, 2024; Gemma 2 2B IT came out Jul 31, 2024. Knowledge cutoff: Gemma 3 12B IT Aug 2024, Hermes 3 405B Instruct Dec 31, 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.
