Command R vs Llama-3.3-70B-Instruct vs Mistral Small 3.1 24B
Mistral Small 3.1 24B comes out ahead, 61 to 51 and 42 on our weighted score, though Command R is 6% cheaper per token.
CohereCommand R
51/100- ECI—
- Price$0.15 / $0.60
- Context128K
MetaLlama-3.3-70B-Instruct
42/100- ECI127.3
- Price$0.59 / $0.724
- Context128K
- Our pick
Mistral AIMistral Small 3.1 24B
61/100- ECI127.5
- Price$0.229 / $0.436
- Context128K
Mistral Small 3.1 24B is our pick
Mistral Small 3.1 24B is the better all-round choice, scoring 61/100 against Command R (51) and Llama-3.3-70B-Instruct (42). It leads on 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 priceCommand RCommand R $0.263 · Mistral Small 3.1 24B $0.281 · Llama-3.3-70B-Instruct $0.624 per 1M tokens (3:1 blend)
- Longest contextAbout the sameCommand R 128,000 · Llama-3.3-70B-Instruct 128,000 · Mistral Small 3.1 24B 128,000 tokens
- Widest inputsMistral Small 3.1 24BCommand R: Text · Llama-3.3-70B-Instruct: Text · Mistral Small 3.1 24B: Text, Images
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Command R | Llama-3.3-70B-Instruct | Mistral Small 3.1 24B |
|---|---|---|---|---|
| Price | 50% | 77 | 60 | 76 |
| Inputs & features | 30% | 25 | 25 | 60 |
| Context window | 20% | 24 | 24 | 24 |
| Overall | 100% | 51/100 | 42/100 | 61/100 |
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 | Command RCohere | Llama-3.3-70B-InstructMeta | Mistral Small 3.1 24BMistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 127.3 | 127.5 (best) |
| ECI rank | — | #133 of 148 | #132 of 148 (best) |
| GPQA DiamondGraduate-level science questions | — | 47.4% | 47.5% (best) |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 5.1% | 5.8% (best) |
| Price per million tokens | |||
| Input | $0.15 (best) | $0.59 | $0.229 |
| Output | $0.60 | $0.724 | $0.436 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.263 (best) | $0.624 | $0.281 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Cohere API | Median of 21 providers | Median of 2 providers |
| Limits | |||
| Context window | 128,000 tokens | 128,000 tokens | 128,000 tokens |
| Max output | 4,000 tokens | 4,096 tokens | 16,384 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | command-r-08-2024 | llama-3.3-70b-instruct | — |
| API providers | 5 | 24 (best) | 2 |
| Released | Aug 30, 2024 | Dec 6, 2024 | Mar 17, 2025 |
| Knowledge cutoff | Jun 1, 2024 | Dec 2023 | Jun 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Command R$2.70
- Llama-3.3-70B-Instruct$7.35
- Mistral Small 3.1 24B$3.16
Which should you choose?
Which is better: Command R, Llama-3.3-70B-Instruct or Mistral Small 3.1 24B?
Mistral Small 3.1 24B is the better all-round choice, scoring 61/100 against Command R (51) and Llama-3.3-70B-Instruct (42). It leads on 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, Command R, Llama-3.3-70B-Instruct or Mistral Small 3.1 24B?
Command R is cheaper at $0.15 input / $0.60 output per million tokens (official Cohere API price). Mistral Small 3.1 24B costs $0.229 input / $0.436 output per million tokens (median across 2 API providers); Llama-3.3-70B-Instruct costs $0.59 input / $0.724 output per million tokens (median across 21 API providers; free on Llama). At a typical mix of three input tokens to one output token, that is $0.263 per million tokens for Command R versus $0.281 for Mistral Small 3.1 24B (1.1× as much) and $0.624 for Llama-3.3-70B-Instruct (2.4× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Command R has not been scored yet, Llama-3.3-70B-Instruct has an ECI of 127.3 and Mistral Small 3.1 24B has an ECI of 127.5.
Which is better for coding?
There are no published SWE-bench Verified results for Command R, Llama-3.3-70B-Instruct and Mistral Small 3.1 24B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Command R, Llama-3.3-70B-Instruct and Mistral Small 3.1 24B share the same 128,000-token context window. Maximum output per response: Command R up to 4,000, Llama-3.3-70B-Instruct up to 4,096, Mistral Small 3.1 24B up to 16,384 tokens.
Which can read images, PDFs, audio or video?
Command R accepts text; Llama-3.3-70B-Instruct accepts text; Mistral Small 3.1 24B accepts text and images. Mistral Small 3.1 24B handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights, so you can self-host them.
Which is newer?
Mistral Small 3.1 24B is the newest, released Mar 17, 2025. Llama-3.3-70B-Instruct came out Dec 6, 2024; Command R came out Aug 30, 2024. Knowledge cutoff: Command R Jun 1, 2024, Llama-3.3-70B-Instruct Dec 2023, Mistral Small 3.1 24B Jun 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 Oct 4, 2026.
