Aya Expanse 32B vs Codestral vs Hermes 3 70B Instruct
Codestral comes out ahead, 49 to 32 and 32 on our weighted score, and it is the cheaper option too.
CohereAya Expanse 32B
32/100- ECI—
- Price$0.50 / $1.50
- Context128K
- Our pick
Mistral AICodestral
49/100- ECI—
- Price$0.30 / $0.90
- Context256K
Nous ResearchHermes 3 70B Instruct
32/100- ECI—
- Price$0.70 / $0.70
- Context131K
Codestral is our pick
Codestral is the better all-round choice, scoring 49/100 against Hermes 3 70B Instruct (32) and Aya Expanse 32B (32). It leads on price, inputs & features and context window. 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 priceCodestralCodestral $0.45 · Hermes 3 70B Instruct $0.70 · Aya Expanse 32B $0.75 per 1M tokens (3:1 blend)
- Longest contextCodestralCodestral 256,000 · Hermes 3 70B Instruct 131,072 · Aya Expanse 32B 128,000 tokens
- Widest inputsSame inputsAya Expanse 32B: Text · Codestral: Text · Hermes 3 70B Instruct: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Aya Expanse 32B | Codestral | Hermes 3 70B Instruct |
|---|---|---|---|---|
| Price | 50% | 53 | 64 | 55 |
| Inputs & features | 30% | 0 | 35 | 0 |
| Context window | 20% | 24 | 36 | 25 |
| Overall | 100% | 32/100 | 49/100 | 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 | Aya Expanse 32BCohere | CodestralMistral AI | Hermes 3 70B InstructNous Research |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.50 | $0.30 (best) | $0.70 |
| Output | $1.50 | $0.90 | $0.70 (best) |
| Cached input | — | $0.03 | — |
| Blended (3:1) | $0.75 | $0.45 (best) | $0.70 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Cohere API | Official Mistral API | Median of 5 providers |
| Limits | |||
| Context window | 128,000 tokens | 256,000 tokens (best) | 131,072 tokens |
| Max output | 4,000 tokens | 4,096 tokens | 16,384 tokens (best) |
| 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 | No | No |
| Tool calling | No | Yes | No |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | OpenCC-BY-NC-4.0 | Open | Open |
| API model ID | c4ai-aya-expanse-32b | codestral-latest | — |
| API providers | 2 | 4 | 5 (best) |
| Released | Oct 24, 2024 | May 29, 2024 | Aug 18, 2024 |
| Knowledge cutoff | — | Oct 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.
- Aya Expanse 32B$8.00
- Codestral$4.80
- Hermes 3 70B Instruct$8.40
Which should you choose?
Which is better: Aya Expanse 32B, Codestral or Hermes 3 70B Instruct?
Codestral is the better all-round choice, scoring 49/100 against Hermes 3 70B Instruct (32) and Aya Expanse 32B (32). It leads on price, inputs & features and context window. 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, Aya Expanse 32B, Codestral or Hermes 3 70B Instruct?
Codestral is cheaper at $0.30 input / $0.90 output per million tokens (official Mistral 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 $0.45 per million tokens for Codestral versus $0.70 for Hermes 3 70B Instruct (1.6× as much) and $0.75 for Aya Expanse 32B (1.7× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Aya Expanse 32B has not been scored yet, Codestral has not been scored yet and Hermes 3 70B Instruct has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Aya Expanse 32B, Codestral and Hermes 3 70B Instruct yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Aya Expanse 32B and Hermes 3 70B Instruct does not support tool calling, which most coding agents need.
Which has the bigger context window?
Codestral has the largest context window at 256,000 tokens, against 131,072 for Hermes 3 70B Instruct and 128,000 for Aya Expanse 32B. Maximum output per response: Aya Expanse 32B up to 4,000, Codestral up to 4,096, Hermes 3 70B Instruct up to 16,384 tokens.
Which can read images, PDFs, audio or video?
Aya Expanse 32B accepts text; Codestral accepts text; Hermes 3 70B Instruct accepts text. They handle the same number of input types.
Are any of these open source?
Yes, all three publish their weights (CC-BY-NC-4.0), so you can self-host them.
Which is newer?
Aya Expanse 32B is the newest, released Oct 24, 2024. Hermes 3 70B Instruct came out Aug 18, 2024; Codestral came out May 29, 2024. Knowledge cutoff: Codestral Oct 2024, Hermes 3 70B 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.
