Gemma 2 2B IT vs Hermes 3 405B Instruct vs Mistral Large
Mistral Large comes out ahead, 37 to 10 and 0 on our weighted score, and it is the cheaper option too.
GoogleGemma 2 2B IT
0/100- ECI—
- Price—
- Context8K
Nous ResearchHermes 3 405B Instruct
10/100- ECI—
- Price$1.00 / $1.00
- Context131K
- Our pick
Mistral AIMistral Large
37/100- ECI122.0
- Price$0.50 / $1.50
- Context128K
Mistral Large is our pick
Mistral Large is the better all-round choice, scoring 37/100 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 priceMistral LargeMistral Large $0.75 · Hermes 3 405B Instruct $1.00 per 1M tokens (3:1 blend) · Gemma 2 2B IT unpriced
- Longest contextHermes 3 405B InstructHermes 3 405B Instruct 131,072 · Mistral Large 128,000 · Gemma 2 2B IT 8,192 tokens
- Widest inputsMistral LargeGemma 2 2B IT: Text · Hermes 3 405B Instruct: Text · Mistral Large: Text, PDFs
- Self-hostingGemma 2 2B IT and Hermes 3 405B InstructPublishes downloadable weights (Gemma Terms of Use)
| Measure | Weight | Gemma 2 2B IT | Hermes 3 405B Instruct | Mistral Large |
|---|---|---|---|---|
| Inputs & features | 60% | 0 | 0 | 45 |
| Context window | 40% | 0 | 25 | 24 |
| Overall | 100% | 0/100 | 10/100 | 37/100 |
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 | Hermes 3 405B InstructNous Research | Mistral LargeMistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | 122.0 |
| ECI rank | — | — | #153 of 165 |
| GPQA DiamondGraduate-level science questions | — | — | 38.8% |
| OTIS Mock AIME 2024–2025Competition mathematics | — | — | 1.9% |
| Price per million tokens | |||
| Input | — | $1.00 | $0.50 (best) |
| Output | — | $1.00 (best) | $1.50 |
| Cached input | — | — | $0.05 |
| Blended (3:1) | — | $1.00 | $0.75 (best) |
| Long-context rate | — | Same rate | Same rate |
| Price source | — | Median of 5 providers | Official Mistral API |
| Limits | |||
| Context window | 8,192 tokens | 131,072 tokens (best) | 128,000 tokens |
| Max output | 8,192 tokens | 16,384 tokens | 102,400 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | Yes |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | No | No | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | OpenGemma Terms of Use | Open | Proprietary |
| API model ID | — | — | mistral-large-latest |
| API providers | — | 5 | 11 (best) |
| Released | Jul 31, 2024 | Aug 16, 2024 | Feb 26, 2024 |
| Knowledge cutoff | — | Dec 31, 2023 | Nov 30, 2024 |
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—
- Hermes 3 405B Instruct$12.00
- Mistral Large$8.00
Which should you choose?
Which is better: Gemma 2 2B IT, Hermes 3 405B Instruct or Mistral Large?
Mistral Large is the better all-round choice, scoring 37/100 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, Hermes 3 405B Instruct or Mistral Large?
Mistral Large is cheaper at $0.50 input / $1.50 output per million tokens (official Mistral API price). 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 $0.75 per million tokens for Mistral Large versus $1.00 for Hermes 3 405B Instruct (1.3× 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, Hermes 3 405B Instruct has not been scored yet and Mistral Large has an ECI of 122.0.
Which is better for coding?
There are no published SWE-bench Verified results for Gemma 2 2B IT, Hermes 3 405B Instruct and Mistral Large 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?
Hermes 3 405B Instruct has the largest context window at 131,072 tokens, against 128,000 for Mistral Large and 8,192 for Gemma 2 2B IT. Maximum output per response: Gemma 2 2B IT up to 8,192, Hermes 3 405B Instruct up to 16,384, Mistral Large up to 102,400 tokens.
Which can read images, PDFs, audio or video?
Gemma 2 2B IT accepts text; Hermes 3 405B Instruct accepts text; Mistral Large accepts text and PDFs. Mistral Large handles the widest range of inputs.
Are any of these open source?
Gemma 2 2B IT and Hermes 3 405B Instruct publishes its weights (Gemma Terms of Use) and can be self-hosted; Mistral Large is proprietary.
Which is newer?
Hermes 3 405B Instruct is the newest, released Aug 16, 2024. Gemma 2 2B IT came out Jul 31, 2024; Mistral Large came out Feb 26, 2024. Knowledge cutoff: Hermes 3 405B Instruct Dec 31, 2023, Mistral Large Nov 30, 2024.
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.
