Codestral vs Hermes 3 70B Instruct vs Qwen Plus
Qwen Plus comes out ahead, 54 to 49 and 32 on our weighted score, though Codestral is 25% cheaper per token.
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
- Our pick
Alibaba (Qwen)Qwen Plus
54/100- ECI—
- Price$0.40 / $1.20
- Context1M
Qwen Plus is our pick
Qwen Plus is the better all-round choice, scoring 54/100 against Codestral (49) and Hermes 3 70B Instruct (32). It leads on inputs & features and context window. Codestral wins on 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 priceCodestralCodestral $0.45 · Qwen Plus $0.60 · Hermes 3 70B Instruct $0.70 per 1M tokens (3:1 blend)
- Longest contextQwen PlusQwen Plus 1,000,000 · Codestral 256,000 · Hermes 3 70B Instruct 131,072 tokens
- Widest inputsSame inputsCodestral: Text · Hermes 3 70B Instruct: Text · Qwen Plus: Text
- Self-hostingCodestral and Hermes 3 70B InstructPublishes downloadable weights
| Measure | Weight | Codestral | Hermes 3 70B Instruct | Qwen Plus |
|---|---|---|---|---|
| Price | 50% | 64 | 55 | 58 |
| Inputs & features | 30% | 35 | 0 | 45 |
| Context window | 20% | 36 | 25 | 60 |
| Overall | 100% | 49/100 | 32/100 | 54/100 |
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 | CodestralMistral AI | Hermes 3 70B InstructNous Research | Qwen PlusAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.30 (best) | $0.70 | $0.40 |
| Output | $0.90 | $0.70 (best) | $1.20 |
| Cached input | $0.03 (best) | — | $0.08 |
| Blended (3:1) | $0.45 (best) | $0.70 | $0.60 |
| Long-context rate | Same rate | Same rate | Over 256K: $1.20 / $3.60 |
| Price source | Official Mistral API | Median of 5 providers | Official Alibaba API |
| Limits | |||
| Context window | 256,000 tokens | 131,072 tokens | 1,000,000 tokens (best) |
| Max output | 4,096 tokens | 16,384 tokens | 32,768 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 | Yes |
| Tool calling | Yes | No | Yes |
| Structured output | Yes | No | Yes |
| Availability | |||
| Weights | Open | Open | Proprietary |
| API model ID | codestral-latest | — | qwen-plus |
| API providers | 4 | 5 | 10 (best) |
| Released | May 29, 2024 | Aug 18, 2024 | Jan 25, 2024 |
| Knowledge cutoff | Oct 2024 | Dec 31, 2023 | Apr 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Codestral$4.80
- Hermes 3 70B Instruct$8.40
- Qwen Plus$6.40
Which should you choose?
Which is better: Codestral, Hermes 3 70B Instruct or Qwen Plus?
Qwen Plus is the better all-round choice, scoring 54/100 against Codestral (49) and Hermes 3 70B Instruct (32). It leads on inputs & features and context window. Codestral wins on 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, Codestral, Hermes 3 70B Instruct or Qwen Plus?
Codestral is cheaper at $0.30 input / $0.90 output per million tokens (official Mistral API price). Qwen Plus costs $0.40 input / $1.20 output per million tokens (official Alibaba API price); 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 $0.45 per million tokens for Codestral versus $0.60 for Qwen Plus (1.3× as much) and $0.70 for Hermes 3 70B Instruct (1.6× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Codestral has not been scored yet, Hermes 3 70B Instruct has not been scored yet and Qwen Plus has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Codestral, Hermes 3 70B Instruct and Qwen Plus 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?
Qwen Plus has the largest context window at 1,000,000 tokens, against 256,000 for Codestral and 131,072 for Hermes 3 70B Instruct. Maximum output per response: Codestral up to 4,096, Hermes 3 70B Instruct up to 16,384, Qwen Plus up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Codestral accepts text; Hermes 3 70B Instruct accepts text; Qwen Plus accepts text. They handle the same number of input types.
Are any of these open source?
Codestral and Hermes 3 70B Instruct publishes its weights and can be self-hosted; Qwen Plus is proprietary.
Which is newer?
Hermes 3 70B Instruct is the newest, released Aug 18, 2024. Codestral came out May 29, 2024; Qwen Plus came out Jan 25, 2024. Knowledge cutoff: Codestral Oct 2024, Hermes 3 70B Instruct Dec 31, 2023, Qwen Plus Apr 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.
