Hermes 3 70B Instruct vs Nemotron Mini 4B Instruct vs Saba
Nemotron Mini 4B Instruct comes out ahead, 25 to 21 and 10 on our weighted score.
Nous ResearchHermes 3 70B Instruct
10/100- ECI—
- Price$0.70 / $0.70
- Context131K
- Our pick
NVIDIANemotron Mini 4B Instruct
25/100- ECI—
- Price—
- Context128K
Mistral AISaba
21/100- ECI—
- Price$0.20 / $0.60
- Context33K
Nemotron Mini 4B Instruct is our pick
Nemotron Mini 4B Instruct is the better all-round choice, scoring 25/100 against Saba (21) and Hermes 3 70B Instruct (10). Saba wins 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 priceSabaSaba $0.30 · Hermes 3 70B Instruct $0.70 per 1M tokens (3:1 blend) · Nemotron Mini 4B Instruct unpriced
- Longest contextHermes 3 70B InstructHermes 3 70B Instruct 131,072 · Nemotron Mini 4B Instruct 128,000 · Saba 32,768 tokens
- Widest inputsSabaHermes 3 70B Instruct: Text · Nemotron Mini 4B Instruct: Text · Saba: Text, PDFs
- Self-hostingHermes 3 70B Instruct and Nemotron Mini 4B InstructPublishes downloadable weights
| Measure | Weight | Hermes 3 70B Instruct | Nemotron Mini 4B Instruct | Saba |
|---|---|---|---|---|
| Inputs & features | 60% | 0 | 25 | 35 |
| Context window | 40% | 25 | 24 | 0 |
| Overall | 100% | 10/100 | 25/100 | 21/100 |
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 | Hermes 3 70B InstructNous Research | Nemotron Mini 4B InstructNVIDIA | SabaMistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.70 | — | $0.20 (best) |
| Output | $0.70 | — | $0.60 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.70 | — | $0.30 (best) |
| Long-context rate | Same rate | — | Same rate |
| Price source | Median of 5 providers | — | Median of 4 providers |
| Limits | |||
| Context window | 131,072 tokens (best) | 128,000 tokens | 32,768 tokens |
| Max output | 16,384 tokens | 8,192 tokens | 26,214 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 | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Open | Proprietary |
| API model ID | — | — | — |
| API providers | 5 (best) | — | 4 |
| Released | Aug 18, 2024 | Aug 21, 2024 | Feb 17, 2025 |
| Knowledge cutoff | Dec 31, 2023 | — | Sep 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.
- Hermes 3 70B Instruct$8.40
- Nemotron Mini 4B Instruct—
- Saba$3.20
Which should you choose?
Which is better: Hermes 3 70B Instruct, Nemotron Mini 4B Instruct or Saba?
Nemotron Mini 4B Instruct is the better all-round choice, scoring 25/100 against Saba (21) and Hermes 3 70B Instruct (10). Saba wins 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, Hermes 3 70B Instruct, Nemotron Mini 4B Instruct or Saba?
Saba is cheaper at $0.20 input / $0.60 output per million tokens (median across 4 API providers). Hermes 3 70B Instruct costs $0.70 input / $0.70 output per million tokens (median across 5 API providers). At a typical mix of three input tokens to one output token, that is $0.30 per million tokens for Saba versus $0.70 for Hermes 3 70B Instruct (2.3× as much). Nemotron Mini 4B Instruct has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Hermes 3 70B Instruct has not been scored yet, Nemotron Mini 4B Instruct has not been scored yet and Saba has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Hermes 3 70B Instruct, Nemotron Mini 4B Instruct and Saba yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Hermes 3 70B Instruct does not support tool calling, which most coding agents need.
Which has the bigger context window?
Hermes 3 70B Instruct has the largest context window at 131,072 tokens, against 128,000 for Nemotron Mini 4B Instruct and 32,768 for Saba. Maximum output per response: Hermes 3 70B Instruct up to 16,384, Nemotron Mini 4B Instruct up to 8,192, Saba up to 26,214 tokens.
Which can read images, PDFs, audio or video?
Hermes 3 70B Instruct accepts text; Nemotron Mini 4B Instruct accepts text; Saba accepts text and PDFs. Saba handles the widest range of inputs.
Are any of these open source?
Hermes 3 70B Instruct and Nemotron Mini 4B Instruct publishes its weights and can be self-hosted; Saba is proprietary.
Which is newer?
Saba is the newest, released Feb 17, 2025. Nemotron Mini 4B Instruct came out Aug 21, 2024; Hermes 3 70B Instruct came out Aug 18, 2024. Knowledge cutoff: Hermes 3 70B Instruct Dec 31, 2023, Saba Sep 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.
