ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Llama-3.3-70B-Instruct vs Llama 4 Scout 17B Instruct vs Magistral Small 1.2

Too close to call on our weighted score (Llama 4 Scout 17B Instruct 43, Magistral Small 1.2 42, Llama-3.3-70B-Instruct 27). The right pick depends on what you value most.

Price in rating: Excluded · Include price

  1. Meta

    Llama-3.3-70B-Instruct

    Released Dec 6, 2024

    27/100
    • ECI126.2
    • Price$0.59 / $0.745
    • Context128K
  2. Meta

    Llama 4 Scout 17B Instruct

    Released Apr 5, 2025

    43/100
    • ECI127.8
    • Price$0.17 / $0.59
    • Context10M
  3. Mistral AI

    Magistral Small 1.2

    Released Sep 18, 2025

    42/100
    • ECI—
    • Price$0.50 / $1.50
    • Context131K
01 — Verdict

Too close to call

It is close. Our weighted score puts them within 2 points (Llama 4 Scout 17B Instruct 43/100, Magistral Small 1.2 42/100, Llama-3.3-70B-Instruct 27/100), so choose by what matters most for your work: Magistral Small 1.2 for raw capability, Llama 4 Scout 17B Instruct on price and Llama 4 Scout 17B Instruct for long inputs. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Magistral Small 1.2 has no Capabilities Index score yet.

  • CapabilityMagistral Small 1.2Shared benchmarks: Magistral Small 1.2 37.8% · Llama 4 Scout 17B Instruct 29.8% · Llama-3.3-70B-Instruct 26.3%
  • Lowest priceLlama 4 Scout 17B InstructLlama 4 Scout 17B Instruct $0.275 · Llama-3.3-70B-Instruct $0.629 · Magistral Small 1.2 $0.75 per 1M tokens (3:1 blend)
  • Longest contextLlama 4 Scout 17B InstructLlama 4 Scout 17B Instruct 10,000,000 · Magistral Small 1.2 131,072 · Llama-3.3-70B-Instruct 128,000 tokens
  • Widest inputsLlama 4 Scout 17B Instruct and Magistral Small 1.2Llama-3.3-70B-Instruct: Text · Llama 4 Scout 17B Instruct: Text, Images · Magistral Small 1.2: Text, Images
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightLlama-3.3-70B-InstructLlama 4 Scout 17B InstructMagistral Small 1.2
CapabilityShared benchmarks67%263038
Inputs & features20%255060
Context window13%3210032
Overall100%27/10043/10042/100
02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Llama-3.3-70B-Instruct vs Llama 4 Scout 17B Instruct vs Magistral Small 1.2 specifications side by side
SpecificationLlama-3.3-70B-InstructMetaLlama 4 Scout 17B InstructMetaMagistral Small 1.2Mistral AI
Capability
Capabilities Index (ECI)126.2127.8 (best)—
ECI rank#144 of 158#140 of 158 (best)—
GPQA DiamondGraduate-level science questions47.4%51.8% (best)47.6%
OTIS Mock AIME 2024–2025Competition mathematics5.1%7.8%28.1% (best)
Price per million tokens
Input$0.59$0.17 (best)$0.50
Output$0.745$0.59 (best)$1.50
Cached input———
Blended (3:1)$0.629$0.275 (best)$0.75
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 40 providersMedian of 13 providersMedian of 1 providers
Limits
Context window128,000 tokens10,000,000 tokens (best)131,072 tokens
Max output4,096 tokens16,384 tokens131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoYesYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoYes
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenOpenOpenApache 2.0
API model ID———
API providers43 (best)131
ReleasedDec 6, 2024Apr 5, 2025Sep 18, 2025
Knowledge cutoffDec 2023Aug 2024—
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Llama-3.3-70B-Instruct$7.39
  • Llama 4 Scout 17B Instruct$2.88
  • Magistral Small 1.2$8.00
04 — Questions

Which should you choose?

Which is better: Llama-3.3-70B-Instruct, Llama 4 Scout 17B Instruct or Magistral Small 1.2?

It is close. Our weighted score puts them within 2 points (Llama 4 Scout 17B Instruct 43/100, Magistral Small 1.2 42/100, Llama-3.3-70B-Instruct 27/100), so choose by what matters most for your work: Magistral Small 1.2 for raw capability, Llama 4 Scout 17B Instruct on price and Llama 4 Scout 17B Instruct for long inputs. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Magistral Small 1.2 has no Capabilities Index score yet.

Which is cheaper, Llama-3.3-70B-Instruct, Llama 4 Scout 17B Instruct or Magistral Small 1.2?

Llama 4 Scout 17B Instruct is cheaper at $0.17 input / $0.59 output per million tokens (median across 13 API providers). Llama-3.3-70B-Instruct costs $0.59 input / $0.745 output per million tokens (median across 40 API providers); Magistral Small 1.2 costs $0.50 input / $1.50 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.275 per million tokens for Llama 4 Scout 17B Instruct versus $0.629 for Llama-3.3-70B-Instruct (2.3× as much) and $0.75 for Magistral Small 1.2 (2.7× 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): Magistral Small 1.2 37.8%, Llama 4 Scout 17B Instruct 29.8% and Llama-3.3-70B-Instruct 26.3%. On individual benchmarks: GPQA Diamond — Llama 4 Scout 17B Instruct 51.8%, Magistral Small 1.2 47.6%, Llama-3.3-70B-Instruct 47.4%; OTIS Mock AIME 2024–2025 — Magistral Small 1.2 28.1%, Llama 4 Scout 17B Instruct 7.8%, Llama-3.3-70B-Instruct 5.1%.

Which is better for coding?

There are no published SWE-bench Verified results for Llama-3.3-70B-Instruct, Llama 4 Scout 17B Instruct and Magistral Small 1.2 yet, so there is no like-for-like coding score. On overall capability, Magistral Small 1.2 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?

Llama 4 Scout 17B Instruct has the largest context window at 10,000,000 tokens, against 131,072 for Magistral Small 1.2 and 128,000 for Llama-3.3-70B-Instruct. Maximum output per response: Llama-3.3-70B-Instruct up to 4,096, Llama 4 Scout 17B Instruct up to 16,384, Magistral Small 1.2 up to 131,072 tokens.

Which can read images, PDFs, audio or video?

Llama-3.3-70B-Instruct accepts text; Llama 4 Scout 17B Instruct accepts text and images; Magistral Small 1.2 accepts text and images. Llama 4 Scout 17B Instruct handles the widest range of inputs.

Are any of these open source?

Yes, all three publish their weights (Apache 2.0), so you can self-host them.

Which is newer?

Magistral Small 1.2 is the newest, released Sep 18, 2025. Llama 4 Scout 17B Instruct came out Apr 5, 2025; Llama-3.3-70B-Instruct came out Dec 6, 2024. Knowledge cutoff: Llama-3.3-70B-Instruct Dec 2023, Llama 4 Scout 17B Instruct Aug 2024.

How do you decide the winner?

This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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.