Sonar Deep Research vs Hermes 3 70B Instruct vs Command A
No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.
Price in rating: Included · Exclude price
Perplexity
Sonar Deep Research
21/100- ECI—
- Price$2.00 / $8.00
- Context128K
Nous Research
Hermes 3 70B Instruct
34/100- ECI—
- Price$0.70 / $0.70
- Context131K
Cohere
Command A
28/100- ECI—
- Price$2.50 / $10.00
- Context256K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Hermes 3 70B Instruct 34/100, Command A 28/100, Sonar Deep Research 21/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. 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 priceHermes 3 70B InstructHermes 3 70B Instruct $0.70 · Sonar Deep Research $3.50 · Command A $4.38 per 1M tokens (3:1 blend)
- Longest contextCommand ACommand A 256,000 · Hermes 3 70B Instruct 131,072 · Sonar Deep Research 128,000 tokens
- Widest inputsSame inputsSonar Deep Research: Text · Hermes 3 70B Instruct: Text · Command A: Text
- Self-hostingHermes 3 70B Instruct and Command APublishes downloadable weights
| Measure | Weight | Sonar Deep Research | Hermes 3 70B Instruct | Command A |
|---|---|---|---|---|
| Price | 50% | 23 | 55 | 19 |
| Inputs & features | 30% | 10 | 0 | 35 |
| Context window | 20% | 32 | 32 | 43 |
| Specs & price only | 100% | 21/100 | 34/100 | 28/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $2.00 | $0.70 (best) | $2.50 |
| Output | $8.00 | $0.70 (best) | $10.00 |
| Cached input | — | — | — |
| Blended (3:1) | $3.50 | $0.70 (best) | $4.38 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Perplexity API | Median of 1 providers | Official Cohere API |
| Limits | |||
| Context window | 128,000 tokens | 131,072 tokens | 256,000 tokens (best) |
| Max output | 32,768 tokens (best) | 16,384 tokens | 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 | Yesminimal · low · medium · high | No | No |
| Tool calling | No | No | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | Proprietary | Open | Open |
| API model ID | sonar-deep-research | — | command-a-03-2025 |
| API providers | 5 | 1 | 7 (best) |
| Released | Feb 1, 2025 | Aug 18, 2024 | Mar 13, 2025 |
| Knowledge cutoff | Jan 2025 | Dec 31, 2023 | Jun 1, 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Sonar Deep Research$36.00
Hermes 3 70B Instruct$8.40
Command A$45.00
Which should you choose?
Which is better: Sonar Deep Research, Hermes 3 70B Instruct or Command A?
There is not enough shared capability evidence to name an overall winner. The scores (Hermes 3 70B Instruct 34/100, Command A 28/100, Sonar Deep Research 21/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Sonar Deep Research, Hermes 3 70B Instruct or Command A?
Hermes 3 70B Instruct is cheaper at $0.70 input / $0.70 output per million tokens (median across 1 API provider). Sonar Deep Research costs $2.00 input / $8.00 output per million tokens (official Perplexity API price); Command A costs $2.50 input / $10.00 output per million tokens (official Cohere API price). At a typical mix of three input tokens to one output token, that is $0.70 per million tokens for Hermes 3 70B Instruct versus $3.50 for Sonar Deep Research (5× as much) and $4.38 for Command A (6.3× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Sonar Deep Research has not been scored yet, Hermes 3 70B Instruct has not been scored yet and Command A has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Sonar Deep Research, Hermes 3 70B Instruct and Command A yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Sonar Deep Research and Hermes 3 70B Instruct does not support tool calling, which most coding agents need.
Which has the bigger context window?
Command A has the largest context window at 256,000 tokens, against 131,072 for Hermes 3 70B Instruct and 128,000 for Sonar Deep Research. Maximum output per response: Sonar Deep Research up to 32,768, Hermes 3 70B Instruct up to 16,384, Command A up to 8,000 tokens.
Which can read images, PDFs, audio or video?
Sonar Deep Research accepts text; Hermes 3 70B Instruct accepts text; Command A accepts text. They handle the same number of input types.
Are any of these open source?
Hermes 3 70B Instruct and Command A publishes its weights and can be self-hosted; Sonar Deep Research is proprietary.
Which is newer?
Command A is the newest, released Mar 13, 2025. Sonar Deep Research came out Feb 1, 2025; Hermes 3 70B Instruct came out Aug 18, 2024. Knowledge cutoff: Sonar Deep Research Jan 2025, Hermes 3 70B Instruct Dec 31, 2023, Command A Jun 1, 2024.
How do you decide the winner?
This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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.