Noometry

Model comparison

Gemini 3.1 Pro Preview vs Magistral Medium

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 35.2 on the Noometry Index. Magistral Medium costs 1.6× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Last verified . 21 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

Magistral Medium Mistral AI

35.2

Rank #227 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 8 categories and Magistral Medium in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 8.6.
  • The biggest single-benchmark swing is ARC-AGI-1: 98% for Gemini 3.1 Pro Preview and 6.1% for Magistral Medium.
  • Magistral Medium is cheaper at $2 / $5 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
  • Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 262K.
  • Magistral Medium has downloadable open weights; the other is API-only.

Side by side

Gemini 3.1 Pro PreviewMagistral Medium
ProviderGoogleMistral AI
Noometry Index56.735.2
Released2026-02-192025-03-17
WeightsProprietaryOpen
Context window1.05M262K
Max output66K16K
Input $ / M tokens$2$2
Output $ / M tokens$12$5
Results tracked7122

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 42.5 (#99), Magistral Medium: 39.1 (#161)

BenchmarkGemini 3.1 Pro PreviewMagistral Medium
SciCode58.9%39.2%
LMArena Coding14841319
SWE-bench Verified75.6%—
DeepSWE11.7%—
LMArena WebDev1447—
GSO22.6%—
WeirdML72.1%—
MirrorCode8.9%—
ALE-Bench1,161—
AlgoTune2.02—

Agentic & Tool Use Not comparable

Gemini 3.1 Pro Preview: 37.7 (#34), Magistral Medium: —

BenchmarkGemini 3.1 Pro PreviewMagistral Medium
Terminal-Bench80.2%—
APEX-Agents35.3%—
τ²-bench Banking26%—
DeepResearch Bench47.8%—
PostTrainBench22%—
BALROG57%—
ExploitBench26.1%—
GBAEval0.8%—
GDP.pdf17%—
LMArena Search1211—
METR Time Horizons77%—
Vending-Bench 23,774—

Reasoning Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.7 (#12), Magistral Medium: 8.6 (#348)

BenchmarkGemini 3.1 Pro PreviewMagistral Medium
ARC-AGI-277.1%0%
ARC-AGI-198%6.1%
CritPt17.7%0.3%
LMArena Hard Prompts14851267
SimpleBench79.6%—
Kagi LLM Benchmark—16.2%
NYT Connections (extended)97.4%—
Chess Puzzles55%—
EnigmaEval36.8%—
Thematic Generalization79.4%—
EBR-Bench14.3%—
Mystery Game Puzzles34%—
DTBench97.1%—
LMCA53.8%—
Epoch Capabilities Index154.77—
ForecastBench59—

Math Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 62.1 (#34), Magistral Medium: 35.1 (#189)

BenchmarkGemini 3.1 Pro PreviewMagistral Medium
LMArena Math14851250
FrontierMath (Tiers 1-3)59.6%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions86.5%—
OTIS Mock AIME 2024-202595.6%—
ProofBench26%—
FrontierMath (Feb 2025 set)36.9%—
FrontierMath Tier 4 (v1)16.7%—

Knowledge Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.8 (#3), Magistral Medium: 33.5 (#202)

BenchmarkGemini 3.1 Pro PreviewMagistral Medium
LMArena Expert14851223
GPQA Diamond94.4%—
Humanity's Last Exam46.4%—
SimpleQA Verified73.5%—
Vectara Hallucination Rate10.4%—

Multimodal Not comparable

Gemini 3.1 Pro Preview: 37.9 (#69), Magistral Medium: —

BenchmarkGemini 3.1 Pro PreviewMagistral Medium
LMArena Vision1296—
Blueprint-Bench 226.5%—
Furniture Assembly26.7%—
LMArena Document1444—

Multilingual Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 57.0 (#12), Magistral Medium: 39.6 (#224)

BenchmarkGemini 3.1 Pro PreviewMagistral Medium
LMArena Non-English14771232
LMArena Chinese15291227
LMArena French14871267
LMArena German14911248
LMArena Japanese14931175
LMArena Korean14551125
LMArena Russian14981224
LMArena Spanish14791271

Instruction Following Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 77.0 (#32), Magistral Medium: 66.0 (#211)

BenchmarkGemini 3.1 Pro PreviewMagistral Medium
LMArena Instruction Following14661254

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.4 (#18), Magistral Medium: 39.3 (#183)

BenchmarkGemini 3.1 Pro PreviewMagistral Medium
LMArena Longer Query14831295
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 66.1 (#37), Magistral Medium: 46.3 (#219)

BenchmarkGemini 3.1 Pro PreviewMagistral Medium
LMArena Text14811255
LMArena Creative Writing14821245
LMArena Multi-Turn14881275
EQ-Bench Creative Writing1491—
EQ-Bench 41142—

Frequently asked questions

Is Gemini 3.1 Pro Preview better than Magistral Medium?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 35.2 on the Noometry Index. Magistral Medium costs 1.6× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Which is cheaper, Gemini 3.1 Pro Preview or Magistral Medium?

Magistral Medium is cheaper. It lists at $2 per million input tokens and $5 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or Magistral Medium better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 39.1 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 262K.

How many benchmarks do Gemini 3.1 Pro Preview and Magistral Medium share?

21 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Magistral Medium has 22.

Related comparisons

Go deeper