AI Models · Open-Source vs Open-Source

MiniMax M3 Open vs Mistral Medium 3.5 Open

MiniMax M3 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.

Choose MiniMax M3 for the lower output price ($1.2/M vs $7.5/M). It also gives you the larger 1M context window.

MiniMax M3 vs Mistral Medium 3.5 specs

SpecMiniMax M3Mistral Medium 3.5
MakerMiniMaxMistral AI
TypeOpen-weightOpen-weight
Context window1M tokens262K tokens
Input price$0.3/M · free self-host$1.5/M · free self-host
Output price$1.2/M · free self-host$7.5/M · free self-host
Vision / multimodalYesYes
Tool / function callingYesYes
Self-hostableYesYes
LicenseMITApache 2.0

Feature comparison

CapabilityMiniMax M3Mistral Medium 3.5
Open weights (downloadable)✓✓
Self-hostable✓✓
Runs fully offline✓✓
Vision / multimodal✓✓
Tool / function calling✓✓
1M+ context window✓✗

Benchmarks: MiniMax M3 vs Mistral Medium 3.5

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

MiniMax M3 delivers 8.5× more intelligence per dollar.
MiniMax M3
Mistral Medium 3.5
Intelligence index
44.4
29.9
Coding index
58.6
46.9
GPQA
92.9%
74.8%
Humanity's Last Exam
37.1%
12.8%
Long Context Reasoning
74%
61%
SciCode
45.4%
39.6%
IFBench
82.9%
68.8%
τ²-Bench
88.9%
94.2%
τ-Bench Banking
13%
14.4%
Terminal-Bench
65.2%
50.6%
Terminal-Bench Hard
42.4%
33.3%
Speed
96.6 tok/s
59.8 tok/s
Latency
1.72s
0.77s
Intelligence per $
84.6
10

Benchmark data by Artificial Analysis.

How MiniMax M3 and Mistral Medium 3.5 score

🏆 Best value & openness: MiniMax M3 (4.9 vs 4.6 / 5)
CriterionMiniMax M3Mistral Medium 3.5
Cost-efficiency4.54.0
Context window5.04.0
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

MiniMax M3 Open

MiniMax · Open-weight

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

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
MiniMax M3 (batch)MiniMax M2.7MiniMax M2.5MiniMax M2.1MiniMax M2MiniMax M1MiniMax M2-herMiniMax-01
Other variants tracked
Mistral Small 4Devstral 2 2512Mistral Large 3 2512Mistral Medium 3.1Mistral Small 3.1 24BMistral Medium 3Ministral 3 14B 2512Mistral Small 3.2 24BMinistral 3 8B 2512Mistral LargeMistral Large 2407Mistral Small 3SabaMinistral 3 3B 2512Mixtral 8x22B InstructCodestral 2508UncensoredVoxtral Small 24B 2507Mistral Nemo

Frequently asked questions

MiniMax M3 vs Mistral Medium 3.5 — which is cheaper?

MiniMax M3 is cheaper on output ($1.2/M vs $7.5/M).

Which has the larger context window?

MiniMax M3 offers the larger context window (1M tokens).

MiniMax M3 vs Mistral Medium 3.5 — which should I pick in 2026?

Choose MiniMax M3 for the lower output price ($1.2/M vs $7.5/M). It also gives you the larger 1M context window.

People also compare

MiMo-V2.5-Pro vs Mistral Medium 3.5DeepSeek V4 Pro vs Mistral Medium 3.5Hy3 vs Mistral Medium 3.5GLM 5.2 vs Mistral Medium 3.5Nemotron 3 Ultra vs Mistral Medium 3.5MiniMax M3 vs o1-pro

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 →