ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Qwen2.5 72B Instruct vs Mistral Large 2.1 vs GPT-4o

GPT-4o comes out ahead, 43 to 40 and 38 on our weighted score, though Qwen2.5 72B Instruct is 44% cheaper per token.

  1. Alibaba (Qwen)

    Qwen2.5 72B Instruct

    Released Sep 19, 2024

    40/100
    • ECI129.0
    • Price$1.40 / $5.60
    • Context131K
    Full specs Remove Qwen2.5 72B Instruct

  2. Mistral AI

    Mistral Large 2.1

    Released Nov 18, 2024

    38/100
    • ECI128.5
    • Price$2.00 / $6.00
    • Context131K
    Full specs Remove Mistral Large 2.1
  3. Our pick

    OpenAI

    GPT-4o

    Released May 13, 2024

    43/100
    • ECI129.0
    • Price$2.50 / $10.00
    • Context128K
    Full specs Remove GPT-4o
01 — Verdict

GPT-4o is our pick

GPT-4o is the better all-round choice, scoring 43/100 against Qwen2.5 72B Instruct (40) and Mistral Large 2.1 (38). It leads on inputs & features. Qwen2.5 72B Instruct wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityQwen2.5 72B InstructCapabilities Index (ECI): Qwen2.5 72B Instruct 129.0 · GPT-4o 129.0 · Mistral Large 2.1 128.5
  • Lowest priceQwen2.5 72B InstructQwen2.5 72B Instruct $2.45 · Mistral Large 2.1 $3.00 · GPT-4o $4.38 per 1M tokens (3:1 blend)
  • Longest contextQwen2.5 72B Instruct and Mistral Large 2.1Qwen2.5 72B Instruct 131,072 · Mistral Large 2.1 131,072 · GPT-4o 128,000 tokens
  • Widest inputsGPT-4oQwen2.5 72B Instruct: Text · Mistral Large 2.1: Text · GPT-4o: Text, Images, PDFs
  • Self-hostingQwen2.5 72B Instruct and Mistral Large 2.1Publishes downloadable weights
How the score is built
MeasureWeightQwen2.5 72B InstructMistral Large 2.1GPT-4o
CapabilityCapabilities Index (ECI)50%525152
Price25%312719
Inputs & features15%252570
Context window10%242424
Overall100%40/10038/10043/100
02 — Side by side

Every spec in one table

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

Qwen2.5 72B Instruct vs Mistral Large 2.1 vs GPT-4o specifications side by side
SpecificationQwen2.5 72B InstructAlibaba (Qwen)Mistral Large 2.1Mistral AIGPT-4oOpenAI
Capability
Capabilities Index (ECI)129.0 (best)128.5129.0
ECI rank#128 of 148 (best)#130 of 148#129 of 148
GPQA DiamondGraduate-level science questions49.2%51.3% (best)48.9%
OTIS Mock AIME 2024–2025Competition mathematics8.1% (best)7.8%6.3%
Price per million tokens
Input$1.40 (best)$2.00$2.50
Output$5.60 (best)$6.00$10.00
Cached input——$1.25
Blended (3:1)$2.45 (best)$3.00$4.38
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Alibaba APIOfficial Mistral APIOfficial OpenAI API
Limits
Context window131,072 tokens (best)131,072 tokens (best)128,000 tokens
Max output8,192 tokens16,384 tokens (best)16,384 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoYes
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsOpenOpenProprietary
API model IDqwen2-5-72b-instructmistral-large-2411gpt-4o
API providers1219 (best)
ReleasedSep 19, 2024Nov 18, 2024May 13, 2024
Knowledge cutoffApr 2024Nov 2024Sep 2023
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.

  • Qwen2.5 72B Instruct$25.20
  • Mistral Large 2.1$32.00
  • GPT-4o$45.00
04 — Questions

Which should you choose?

Which is better: Qwen2.5 72B Instruct, Mistral Large 2.1 or GPT-4o?

GPT-4o is the better all-round choice, scoring 43/100 against Qwen2.5 72B Instruct (40) and Mistral Large 2.1 (38). It leads on inputs & features. Qwen2.5 72B Instruct wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Qwen2.5 72B Instruct, Mistral Large 2.1 or GPT-4o?

Qwen2.5 72B Instruct is cheaper at $1.40 input / $5.60 output per million tokens (official Alibaba API price). Mistral Large 2.1 costs $2.00 input / $6.00 output per million tokens (official Mistral API price); GPT-4o costs $2.50 input / $10.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $2.45 per million tokens for Qwen2.5 72B Instruct versus $3.00 for Mistral Large 2.1 (1.2× as much) and $4.38 for GPT-4o (1.8× as much).

Which scores higher on benchmarks?

Qwen2.5 72B Instruct scores higher on the Capabilities Index (ECI): Qwen2.5 72B Instruct 129.0 (#128 of 148), GPT-4o 129.0 (#129 of 148) and Mistral Large 2.1 128.5 (#130 of 148). The confidence ranges of the top two overlap (123.8–130.7 vs 124.2–131.5), so treat the gap as small. On individual benchmarks: GPQA Diamond — Mistral Large 2.1 51.3%, Qwen2.5 72B Instruct 49.2%, GPT-4o 48.9%; OTIS Mock AIME 2024–2025 — Qwen2.5 72B Instruct 8.1%, Mistral Large 2.1 7.8%, GPT-4o 6.3%.

Which is better for coding?

There are no published SWE-bench Verified results for Qwen2.5 72B Instruct, Mistral Large 2.1 and GPT-4o yet, so there is no like-for-like coding score. On overall capability, Qwen2.5 72B Instruct 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?

Qwen2.5 72B Instruct and Mistral Large 2.1 have the largest context windows (131,072 and 131,072 tokens), against 128,000 for GPT-4o. Maximum output per response: Qwen2.5 72B Instruct up to 8,192, Mistral Large 2.1 up to 16,384, GPT-4o up to 16,384 tokens.

Which can read images, PDFs, audio or video?

Qwen2.5 72B Instruct accepts text; Mistral Large 2.1 accepts text; GPT-4o accepts text, images and PDFs. GPT-4o handles the widest range of inputs.

Are any of these open source?

Qwen2.5 72B Instruct and Mistral Large 2.1 publishes its weights and can be self-hosted; GPT-4o is proprietary.

Which is newer?

Mistral Large 2.1 is the newest, released Nov 18, 2024. Qwen2.5 72B Instruct came out Sep 19, 2024; GPT-4o came out May 13, 2024. Knowledge cutoff: Qwen2.5 72B Instruct Apr 2024, Mistral Large 2.1 Nov 2024, GPT-4o Sep 2023.

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.

05 — Keep comparing

Related comparisons