ZMIME
Comparison · 3 models · Updated Nov 2, 2026

Gemma 2 27B vs Mistral Large 2407 vs Mixtral 8x22B Instruct

Mistral Large 2407 comes out ahead, 39 to 35 and 34 on our weighted score, though Gemma 2 27B is 4.6× cheaper per token.

  1. Google

    Gemma 2 27B

    Released Jul 13, 2024

    35/100
    • ECI122.1
    • Price$0.65 / $0.65
    • Context8K
    Full specs Remove Gemma 2 27B
  2. Our pick

    Mistral AI

    Mistral Large 2407

    Released Jul 24, 2024

    39/100
    • ECI127.6
    • Price$2.00 / $6.00
    • Context131K
    Full specs Remove Mistral Large 2407

  3. Mistral AI

    Mixtral 8x22B Instruct

    Released Apr 17, 2024

    34/100
    • ECI122.0
    • Price$2.00 / $6.00
    • Context66K
    Full specs Remove Mixtral 8x22B Instruct
01 — Verdict

Mistral Large 2407 is our pick

Mistral Large 2407 is the better all-round choice, scoring 39/100 against Gemma 2 27B (35) and Mixtral 8x22B Instruct (34). It leads on capability and context window. Gemma 2 27B wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityMistral Large 2407Capabilities Index (ECI): Mistral Large 2407 127.6 · Gemma 2 27B 122.1 · Mixtral 8x22B Instruct 122.0
  • Lowest priceGemma 2 27BGemma 2 27B $0.65 · Mistral Large 2407 $3.00 · Mixtral 8x22B Instruct $3.00 per 1M tokens (3:1 blend)
  • Longest contextMistral Large 2407Mistral Large 2407 131,072 · Mixtral 8x22B Instruct 65,536 · Gemma 2 27B 8,192 tokens
  • Widest inputsMistral Large 2407 and Mixtral 8x22B InstructGemma 2 27B: Text · Mistral Large 2407: Text, PDFs · Mixtral 8x22B Instruct: Text, PDFs
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightGemma 2 27BMistral Large 2407Mixtral 8x22B Instruct
CapabilityCapabilities Index (ECI)50%424942
Price25%562626
Inputs & features15%03535
Context window10%02512
Overall100%35/10039/10034/100
02 — Side by side

Every spec in one table

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

Gemma 2 27B vs Mistral Large 2407 vs Mixtral 8x22B Instruct specifications side by side
SpecificationGemma 2 27BGoogleMistral Large 2407Mistral AIMixtral 8x22B InstructMistral AI
Capability
Capabilities Index (ECI)122.1127.6 (best)122.0
ECI rank#152 of 165#144 of 165 (best)#155 of 165
GPQA DiamondGraduate-level science questions36.5%49.0% (best)34.1%
OTIS Mock AIME 2024–2025Competition mathematics1.4%8.5% (best)—
Price per million tokens
Input$0.65 (best)$2.00$2.00
Output$0.65 (best)$6.00$6.00
Cached input———
Blended (3:1)$0.65 (best)$3.00$3.00
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 3 providersMedian of 5 providersMedian of 5 providers
Limits
Context window8,192 tokens131,072 tokens (best)65,536 tokens
Max output2,048 tokens104,857 tokens (best)52,428 tokens
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoYesYes
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingNoYesYes
Structured outputNoNoNo
Availability
WeightsOpenOpenOpen
API model ID———
API providers35 (best)5 (best)
ReleasedJul 13, 2024Jul 24, 2024Apr 17, 2024
Knowledge cutoffJun 30, 2024Mar 31, 2024Jan 31, 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.

  • Gemma 2 27B$7.80
  • Mistral Large 2407$32.00
  • Mixtral 8x22B Instruct$32.00
04 — Questions

Which should you choose?

Which is better: Gemma 2 27B, Mistral Large 2407 or Mixtral 8x22B Instruct?

Mistral Large 2407 is the better all-round choice, scoring 39/100 against Gemma 2 27B (35) and Mixtral 8x22B Instruct (34). It leads on capability and context window. Gemma 2 27B wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Gemma 2 27B, Mistral Large 2407 or Mixtral 8x22B Instruct?

Gemma 2 27B is cheaper at $0.65 input / $0.65 output per million tokens (median across 3 API providers). Mistral Large 2407 costs $2.00 input / $6.00 output per million tokens (median across 5 API providers); Mixtral 8x22B Instruct costs $2.00 input / $6.00 output per million tokens (median across 5 API providers). At a typical mix of three input tokens to one output token, that is $0.65 per million tokens for Gemma 2 27B versus $3.00 for Mistral Large 2407 (4.6× as much) and $3.00 for Mixtral 8x22B Instruct (4.6× as much).

Which scores higher on benchmarks?

Mistral Large 2407 scores higher on the Capabilities Index (ECI): Mistral Large 2407 127.6 (#144 of 165), Gemma 2 27B 122.1 (#152 of 165) and Mixtral 8x22B Instruct 122.0 (#155 of 165). The confidence ranges of the top two overlap (123.3–129.4 vs 115.8–124.1), so treat the gap as small. On individual benchmarks: GPQA Diamond — Mistral Large 2407 49.0%, Gemma 2 27B 36.5%, Mixtral 8x22B Instruct 34.1%.

Which is better for coding?

There are no published SWE-bench Verified results for Gemma 2 27B, Mistral Large 2407 and Mixtral 8x22B Instruct yet, so there is no like-for-like coding score. On overall capability, Mistral Large 2407 leads, which tends to carry over to coding, but test on your own codebase. Note that Gemma 2 27B does not support tool calling, which most coding agents need.

Which has the bigger context window?

Mistral Large 2407 has the largest context window at 131,072 tokens, against 65,536 for Mixtral 8x22B Instruct and 8,192 for Gemma 2 27B. Maximum output per response: Gemma 2 27B up to 2,048, Mistral Large 2407 up to 104,857, Mixtral 8x22B Instruct up to 52,428 tokens.

Which can read images, PDFs, audio or video?

Gemma 2 27B accepts text; Mistral Large 2407 accepts text and PDFs; Mixtral 8x22B Instruct accepts text and PDFs. Mistral Large 2407 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 Large 2407 is the newest, released Jul 24, 2024. Gemma 2 27B came out Jul 13, 2024; Mixtral 8x22B Instruct came out Apr 17, 2024. Knowledge cutoff: Gemma 2 27B Jun 30, 2024, Mistral Large 2407 Mar 31, 2024, Mixtral 8x22B Instruct Jan 31, 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 Nov 2, 2026.

05 — Keep comparing

Related comparisons