Hermes 3 70B Instruct vs Solar Pro 2 vs Aya Expanse 32B
Solar Pro 2 comes out ahead, 51 to 32 and 32 on our weighted score, and it is the cheaper option too.
Nous ResearchHermes 3 70B Instruct
32/100- ECI—
- Price$0.70 / $0.70
- Context131K
- Our pick
UpstageSolar Pro 2
51/100- ECI—
- Price$0.25 / $0.25
- Context66K
CohereAya Expanse 32B
32/100- ECI—
- Price$0.50 / $1.50
- Context128K
Solar Pro 2 is our pick
Solar Pro 2 is the better all-round choice, scoring 51/100 against Hermes 3 70B Instruct (32) and Aya Expanse 32B (32). It leads on price and inputs & features. 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 priceSolar Pro 2Solar Pro 2 $0.25 · Hermes 3 70B Instruct $0.70 · Aya Expanse 32B $0.75 per 1M tokens (3:1 blend)
- Longest contextHermes 3 70B InstructHermes 3 70B Instruct 131,072 · Aya Expanse 32B 128,000 · Solar Pro 2 65,536 tokens
- Widest inputsSame inputsHermes 3 70B Instruct: Text · Solar Pro 2: Text · Aya Expanse 32B: Text
- Self-hostingHermes 3 70B Instruct and Aya Expanse 32BPublishes downloadable weights (CC-BY-NC-4.0)
| Measure | Weight | Hermes 3 70B Instruct | Solar Pro 2 | Aya Expanse 32B |
|---|---|---|---|---|
| Price | 50% | 55 | 75 | 53 |
| Inputs & features | 30% | 0 | 35 | 0 |
| Context window | 20% | 25 | 12 | 24 |
| Overall | 100% | 32/100 | 51/100 | 32/100 |
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 | Hermes 3 70B InstructNous Research | Solar Pro 2Upstage | Aya Expanse 32BCohere |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.70 | $0.25 (best) | $0.50 |
| Output | $0.70 | $0.25 (best) | $1.50 |
| Cached input | — | — | — |
| Blended (3:1) | $0.70 | $0.25 (best) | $0.75 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 5 providers | Official Upstage API | Official Cohere API |
| Limits | |||
| Context window | 131,072 tokens (best) | 65,536 tokens | 128,000 tokens |
| Max output | 16,384 tokens (best) | 8,192 tokens | 4,000 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 | No | Yesminimal · high | No |
| Tool calling | No | Yes | No |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Proprietary | OpenCC-BY-NC-4.0 |
| API model ID | — | solar-pro2 | c4ai-aya-expanse-32b |
| API providers | 5 (best) | 2 | 2 |
| Released | Aug 18, 2024 | May 20, 2025 | Oct 24, 2024 |
| Knowledge cutoff | Dec 31, 2023 | Mar 2025 | — |
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
- Solar Pro 2$3.00
- Aya Expanse 32B$8.00
Which should you choose?
Which is better: Hermes 3 70B Instruct, Solar Pro 2 or Aya Expanse 32B?
Solar Pro 2 is the better all-round choice, scoring 51/100 against Hermes 3 70B Instruct (32) and Aya Expanse 32B (32). It leads on price and inputs & features. 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, Hermes 3 70B Instruct, Solar Pro 2 or Aya Expanse 32B?
Solar Pro 2 is cheaper at $0.25 input / $0.25 output per million tokens (official Upstage API price). Hermes 3 70B Instruct costs $0.70 input / $0.70 output per million tokens (median across 5 API providers); Aya Expanse 32B costs $0.50 input / $1.50 output per million tokens (official Cohere API price). At a typical mix of three input tokens to one output token, that is $0.25 per million tokens for Solar Pro 2 versus $0.70 for Hermes 3 70B Instruct (2.8× as much) and $0.75 for Aya Expanse 32B (3× as much).
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, Solar Pro 2 has not been scored yet and Aya Expanse 32B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Hermes 3 70B Instruct, Solar Pro 2 and Aya Expanse 32B 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 and Aya Expanse 32B 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 Aya Expanse 32B and 65,536 for Solar Pro 2. Maximum output per response: Hermes 3 70B Instruct up to 16,384, Solar Pro 2 up to 8,192, Aya Expanse 32B up to 4,000 tokens.
Which can read images, PDFs, audio or video?
Hermes 3 70B Instruct accepts text; Solar Pro 2 accepts text; Aya Expanse 32B accepts text. They handle the same number of input types.
Are any of these open source?
Hermes 3 70B Instruct and Aya Expanse 32B publishes its weights (CC-BY-NC-4.0) and can be self-hosted; Solar Pro 2 is proprietary.
Which is newer?
Solar Pro 2 is the newest, released May 20, 2025. Aya Expanse 32B came out Oct 24, 2024; Hermes 3 70B Instruct came out Aug 18, 2024. Knowledge cutoff: Hermes 3 70B Instruct Dec 31, 2023, Solar Pro 2 Mar 2025.
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.
