AI Models · Open-Source vs Open-Source

Gemma 4 26B A4B Open vs Mistral Medium 3.5 Open

Gemma 4 26B A4B vs Mistral Medium 3.5 compared — price per token, context window, multimodality, openness and which to choose. Full 2026 breakdown.

Prices & specs refreshed from live data · olud.ai

Open-model prices = cheapest provider via OpenRouter; official maker rates may be higher.

Gemma 4 26B A4BOpenGoogle
$0.04 /M input
$0.22 /M outputNo per-token fees if you self-host
TypeOpen-weight
Context window262K tokens
MultimodalYes
Self-hostYes
Mistral Medium 3.5OpenMistral AI
$1.5 /M input
$7.5 /M outputNo per-token fees if you self-host
TypeOpen-weight
Context window262K tokens
MultimodalYes
Self-hostYes
Choose Gemma 4 26B A4B for the lower output price ($0.22/M vs $7.5/M). It also gives you the larger 262K context window.

Gemma 4 26B A4B vs Mistral Medium 3.5 specs

SpecGemma 4 26B A4BMistral Medium 3.5Winner
MakerGoogleMistral AI–
TypeOpen-weightOpen-weight–
Context window262K tokens262K tokens= Tie
Input price$0.04/M · free self-host$1.5/M · free self-hostGemma 4 26B A4B
Output price$0.22/M · free self-host$7.5/M · free self-hostGemma 4 26B A4B
Vision / multimodalYesYes= Tie
Tool / function callingYesYes= Tie
Self-hostableYesYes= Tie
LicenseGemma LicenseApache 2.0–

Price gap & when to choose each

34×cheaper per output token

Gemma 4 26B A4B is ~34× cheaper than Mistral Medium 3.5 on output tokens ($0.22 vs $7.5 per M tokens).

Choose Gemma 4 26B A4B if…
  • You want to self-host or run on your cloud
  • You prioritize data privacy & control
  • You want the lowest operating costs
  • You are building open or reproducible AI
Choose Mistral Medium 3.5 if…
  • You want to self-host or run on your cloud
  • You prioritize data privacy & control
  • You are building open or reproducible AI

Feature comparison

CapabilityGemma 4 26B A4BMistral Medium 3.5
Open weights (downloadable)✓✓
Self-hostable✓✓
Runs fully offline✓✓
Vision / multimodal✓✓
Tool / function calling✓✓
1M+ context window✗✗

Benchmarks: Gemma 4 26B A4B vs Mistral Medium 3.5

Independent benchmark scores measured by Artificial Analysis. Higher is better (except latency).

Gemma 4 26B A4B delivers 19× more intelligence per dollar.
Gemma 4 26B A4B
Mistral Medium 3.5
Intelligence index
16.7
14.9
Coding index
39.3
46.9
GPQA
79.2%
74.8%
Humanity's Last Exam
19.3%
13.8%
Long Context Reasoning
65.7%
69.3%
IFBench
72.4%
68.8%
τ²-Bench
43.6%
94.2%
τ-Bench Banking
12%
15.1%
Terminal-Bench
39%
50.6%
Terminal-Bench Hard
13.6%
33.3%
SciCode
–
40.2%
Speed
0 tok/s
142.2 tok/s
Latency
0s
0.74s
Intelligence per $
93.3
5

Benchmark data by Artificial Analysis.

How Gemma 4 26B A4B and Mistral Medium 3.5 score

🤝 Neck and neck on these criteria (4.8 vs 4.6 / 5).
CriterionGemma 4 26B A4BMistral Medium 3.5
Cost-efficiency5.04.0
Context window4.04.0
Openness5.05.0
Self-hosting5.05.0
Multimodality5.05.0

Scores come from live data — output price (cost), context length, open vs closed weights (openness & self-hosting) and vision/tool support (multimodality). Raw task quality isn't scored here; it depends on your benchmark — see the verdict.

What each model is

Gemma 4 26B A4B Open

Google · Open-weight

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Mistral Medium 3.5 Open

Mistral AI · Open-weight

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...

Other models in these families

These variants are tracked but not compared here — one page per family keeps the comparison readable.

Other variants tracked
Gemma 4 26B A4B (free)Gemma 4 31B (batch)Gemma 4 31BGemma 4 31B (free)Gemma 3 27BGemma 3 4BGemma 3 12BGemma 2 27B
Other variants tracked
Mistral Medium 3.5 (batch)Mistral Small 4Mistral Small 4 (batch)Mistral Medium 3.1Mistral Medium 3.1 (batch)Mistral Large 3 2512Mistral Large 3 2512 (batch)Devstral 2 2512Mistral Medium 3Mistral Small 3.1 24BMistral Small 3.2 24BMistral LargeMistral Large 2407Mistral Small 3SabaMinistral 3 14B 2512Mixtral 8x22B InstructMinistral 3 8B 2512Ministral 3 8B 2512 (batch)Ministral 3 3B 2512UncensoredCodestral 2508Codestral 2508 (batch)Voxtral Small 24B 2507Mistral Nemo

Frequently asked questions

Gemma 4 26B A4B vs Mistral Medium 3.5 — which is cheaper?

Gemma 4 26B A4B is cheaper on output ($0.22/M vs $7.5/M).

Which has the larger context window?

Gemma 4 26B A4B offers the larger context window (262K tokens).

Gemma 4 26B A4B vs Mistral Medium 3.5 — which should I pick in 2026?

Choose Gemma 4 26B A4B for the lower output price ($0.22/M vs $7.5/M). It also gives you the larger 262K context window.

People also compare

Hy3 vs Mistral Medium 3.5GLM 5.3 vs Mistral Medium 3.5DeepSeek V4.1 Flash vs Mistral Medium 3.5MiMo-V2.5-Pro vs Mistral Medium 3.5Nemotron 3 Ultra vs Mistral Medium 3.5Kimi K3 (batch) vs Mistral Medium 3.5

Explore more open-source AI

Browse the full open-source model leaderboard, thousands of tools and live benchmarks — all in one place.

Open the leaderboard →