Command R vs GPT-4o mini vs Mistral Small 3.1 24B
GPT-4o mini comes out ahead, 64 to 61 and 51 on our weighted score.
CohereCommand R
51/100- ECI—
- Price$0.15 / $0.60
- Context128K
- Our pick
OpenAIGPT-4o mini
64/100- ECI126.6
- Price$0.15 / $0.60
- Context128K
Mistral AIMistral Small 3.1 24B
61/100- ECI127.5
- Price$0.229 / $0.436
- Context128K
GPT-4o mini is our pick
GPT-4o mini is the better all-round choice, scoring 64/100 against Mistral Small 3.1 24B (61) and Command R (51). 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 R and GPT-4o miniCommand R $0.263 · GPT-4o mini $0.263 · Mistral Small 3.1 24B $0.281 per 1M tokens (3:1 blend)
- Longest contextAbout the sameCommand R 128,000 · GPT-4o mini 128,000 · Mistral Small 3.1 24B 128,000 tokens
- Widest inputsGPT-4o miniCommand R: Text · GPT-4o mini: Text, Images, PDFs · Mistral Small 3.1 24B: Text, Images
- Self-hostingCommand R and Mistral Small 3.1 24BPublishes downloadable weights
| Measure | Weight | Command R | GPT-4o mini | Mistral Small 3.1 24B |
|---|---|---|---|---|
| Price | 50% | 77 | 77 | 76 |
| Inputs & features | 30% | 25 | 70 | 60 |
| Context window | 20% | 24 | 24 | 24 |
| Overall | 100% | 51/100 | 64/100 | 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 | GPT-4o miniOpenAI | Mistral Small 3.1 24BMistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 126.6 | 127.5 (best) |
| ECI rank | — | #135 of 148 | #132 of 148 (best) |
| GPQA DiamondGraduate-level science questions | — | 37.7% | 47.5% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | — | 0.7% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 6.9% (best) | 5.8% |
| SimpleQA VerifiedShort factual questions | — | 8.3% | — |
| Price per million tokens | |||
| Input | $0.15 (best) | $0.15 (best) | $0.229 |
| Output | $0.60 | $0.60 | $0.436 (best) |
| Cached input | — | $0.075 | — |
| Blended (3:1) | $0.263 (best) | $0.263 (best) | $0.281 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Cohere API | Official OpenAI API | Median of 2 providers |
| Limits | |||
| Context window | 128,000 tokens | 128,000 tokens | 128,000 tokens |
| Max output | 4,000 tokens | 16,384 tokens (best) | 16,384 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | Yes | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | Yes |
| Availability | |||
| Weights | Open | Proprietary | Open |
| API model ID | command-r-08-2024 | gpt-4o-mini | — |
| API providers | 5 | 21 (best) | 2 |
| Released | Aug 30, 2024 | Jul 18, 2024 | Mar 17, 2025 |
| Knowledge cutoff | Jun 1, 2024 | Sep 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
- GPT-4o mini$2.70
- Mistral Small 3.1 24B$3.16
Which should you choose?
Which is better: Command R, GPT-4o mini or Mistral Small 3.1 24B?
GPT-4o mini is the better all-round choice, scoring 64/100 against Mistral Small 3.1 24B (61) and Command R (51). 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, GPT-4o mini or Mistral Small 3.1 24B?
Command R is cheaper at $0.15 input / $0.60 output per million tokens (official Cohere API price). GPT-4o mini costs $0.15 input / $0.60 output per million tokens (official OpenAI API price); Mistral Small 3.1 24B costs $0.229 input / $0.436 output per million tokens (median across 2 API providers). At a typical mix of three input tokens to one output token, that is $0.263 per million tokens for Command R versus $0.263 for GPT-4o mini (1× as much) and $0.281 for Mistral Small 3.1 24B (1.1× 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, GPT-4o mini has an ECI of 126.6 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, GPT-4o mini 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, GPT-4o mini and Mistral Small 3.1 24B share the same 128,000-token context window. Maximum output per response: Command R up to 4,000, GPT-4o mini up to 16,384, Mistral Small 3.1 24B up to 16,384 tokens.
Which can read images, PDFs, audio or video?
Command R accepts text; GPT-4o mini accepts text, images and PDFs; Mistral Small 3.1 24B accepts text and images. GPT-4o mini handles the widest range of inputs.
Are any of these open source?
Command R and Mistral Small 3.1 24B publishes its weights and can be self-hosted; GPT-4o mini is proprietary.
Which is newer?
Mistral Small 3.1 24B is the newest, released Mar 17, 2025. Command R came out Aug 30, 2024; GPT-4o mini came out Jul 18, 2024. Knowledge cutoff: Command R Jun 1, 2024, GPT-4o mini Sep 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.
