DeepSeek-V3 vs Llama-3.3-70B-Instruct vs Mistral Small 3.1 24B
Too close to call on our weighted score (Mistral Small 3.1 24B 40, DeepSeek-V3 40, Llama-3.3-70B-Instruct 34). The right pick depends on what you value most.
Price in rating: Included · Exclude price
DeepSeek
DeepSeek-V3
40/100- ECI131.7
- Price$0.32 / $1.10
- Context131K
Meta
Llama-3.3-70B-Instruct
34/100- ECI126.2
- Price$0.59 / $0.745
- Context128K
Mistral AI
Mistral Small 3.1 24B
40/100- ECI—
- Price$0.351 / $0.555
- Context128K
Too close to call
It is close. Our weighted score puts them within a point (Mistral Small 3.1 24B 40/100, DeepSeek-V3 40/100, Llama-3.3-70B-Instruct 34/100), so choose by what matters most for your work: DeepSeek-V3 for raw capability and Mistral Small 3.1 24B on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Mistral Small 3.1 24B has no Capabilities Index score yet.
- CapabilityDeepSeek-V3Shared benchmarks: DeepSeek-V3 36.2% · Mistral Small 3.1 24B 26.7% · Llama-3.3-70B-Instruct 26.3%
- Lowest priceMistral Small 3.1 24BMistral Small 3.1 24B $0.402 · DeepSeek-V3 $0.515 · Llama-3.3-70B-Instruct $0.629 per 1M tokens (3:1 blend)
- Longest contextDeepSeek-V3DeepSeek-V3 131,072 · Llama-3.3-70B-Instruct 128,000 · Mistral Small 3.1 24B 128,000 tokens
- Widest inputsMistral Small 3.1 24BDeepSeek-V3: 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 | DeepSeek-V3 | Llama-3.3-70B-Instruct | Mistral Small 3.1 24B |
|---|---|---|---|---|
| CapabilityShared benchmarks | 50% | 36 | 26 | 27 |
| Price | 25% | 61 | 57 | 66 |
| Inputs & features | 15% | 25 | 25 | 50 |
| Context window | 10% | 32 | 32 | 32 |
| Overall | 100% | 40/100 | 34/100 | 40/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 131.7 (best) | 126.2 | — |
| ECI rank | #136 of 158 (best) | #144 of 158 | — |
| GPQA DiamondGraduate-level science questions | 56.5% (best) | 47.4% | 47.5% |
| OTIS Mock AIME 2024–2025Competition mathematics | 15.8% (best) | 5.1% | 5.8% |
| Price per million tokens | |||
| Input | $0.32 (best) | $0.59 | $0.351 |
| Output | $1.10 | $0.745 | $0.555 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.515 | $0.629 | $0.402 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 9 providers | Median of 40 providers | Median of 9 providers |
| Limits | |||
| Context window | 131,072 tokens (best) | 128,000 tokens | 128,000 tokens |
| Max output | 8,192 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 | No |
| Availability | |||
| Weights | OpenDeepSeek Model License | Open | Open |
| API model ID | — | — | — |
| API providers | 9 | 43 (best) | 9 |
| Released | Dec 26, 2024 | Dec 6, 2024 | Mar 17, 2025 |
| Knowledge cutoff | — | 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.
DeepSeek-V3$5.40
Llama-3.3-70B-Instruct$7.39
Mistral Small 3.1 24B$4.62
Which should you choose?
Which is better: DeepSeek-V3, Llama-3.3-70B-Instruct or Mistral Small 3.1 24B?
It is close. Our weighted score puts them within a point (Mistral Small 3.1 24B 40/100, DeepSeek-V3 40/100, Llama-3.3-70B-Instruct 34/100), so choose by what matters most for your work: DeepSeek-V3 for raw capability and Mistral Small 3.1 24B on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Mistral Small 3.1 24B has no Capabilities Index score yet.
Which is cheaper, DeepSeek-V3, Llama-3.3-70B-Instruct or Mistral Small 3.1 24B?
Mistral Small 3.1 24B is cheaper at $0.351 input / $0.555 output per million tokens (median across 9 API providers). DeepSeek-V3 costs $0.32 input / $1.10 output per million tokens (median across 9 API providers); Llama-3.3-70B-Instruct costs $0.59 input / $0.745 output per million tokens (median across 40 API providers). At a typical mix of three input tokens to one output token, that is $0.402 per million tokens for Mistral Small 3.1 24B versus $0.515 for DeepSeek-V3 (1.3× as much) and $0.629 for Llama-3.3-70B-Instruct (1.6× as much).
Which scores higher on benchmarks?
Not every model here has a Capabilities Index score, so we compare the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025): DeepSeek-V3 36.2%, Mistral Small 3.1 24B 26.7% and Llama-3.3-70B-Instruct 26.3%. On individual benchmarks: GPQA Diamond — DeepSeek-V3 56.5%, Mistral Small 3.1 24B 47.5%, Llama-3.3-70B-Instruct 47.4%; OTIS Mock AIME 2024–2025 — DeepSeek-V3 15.8%, Mistral Small 3.1 24B 5.8%, Llama-3.3-70B-Instruct 5.1%.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek-V3, Llama-3.3-70B-Instruct and Mistral Small 3.1 24B yet, so there is no like-for-like coding score. On overall capability, DeepSeek-V3 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
DeepSeek-V3 has the largest context window at 131,072 tokens, against 128,000 for Llama-3.3-70B-Instruct and 128,000 for Mistral Small 3.1 24B. Maximum output per response: DeepSeek-V3 up to 8,192, 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?
DeepSeek-V3 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 (DeepSeek Model License), so you can self-host them.
Which is newer?
Mistral Small 3.1 24B is the newest, released Mar 17, 2025. DeepSeek-V3 came out Dec 26, 2024; Llama-3.3-70B-Instruct came out Dec 6, 2024. Knowledge cutoff: Llama-3.3-70B-Instruct Dec 2023, Mistral Small 3.1 24B Jun 2024.
How do you decide the winner?
This rating uses 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 18, 2026.